docs: add DLO DP behavior animation

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-08 11:55:51 +08:00
167 changed files with 2267 additions and 10779 deletions
@@ -404,7 +404,7 @@ steps:
      - label: ":full_moon: Diffusion X2V · LingBot Video MoE Function Test"
        timeout_in_minutes: 90
        commands:
-          - pytest -s -v tests/e2e/online_serving/test_lingbot_video_moe.py -k "video_generation" -m "full_model and cuda" --run-level "full_model"
+          - pytest -s -v tests/e2e/online_serving/test_lingbot_video_moe.py -m "full_model and cuda" --run-level "full_model"
        mirror_hardwares: h100_1

      - label: ":full_moon: Diffusion X2V · Doc Test"
@@ -220,70 +220,65 @@ See `plan/voxcpm2_native_ar_design.md`.

 ### Steps

-1. **Write one adapter** under `vllm_omni/entrypoints/openai/tts_adapters/`.
-   `serving_speech.py` should not need an edit — detection, stage discovery and
-   dispatch are all derived from what the adapter declares.
+1. **Register in `serving_speech.py`** — add all 5 points in a **single commit**;
+   partial integration causes hard-to-debug failures. This file is modified by every
+   model PR and is the most common source of rebase conflicts — see conflict note below.

-   Create `vllm_omni/entrypoints/openai/tts_adapters/your_model.py`:
+   **Point 1** — stage constant (near the top, alongside the other `_*_TTS_MODEL_STAGES` sets):
   ```python
-   @register_tts_adapter
-   class YourModelAdapter(ARTTSAdapter):
-       name = "your_model"                              # registry key + log label
-       stage_keys = frozenset({"your_stage_key"})       # the deploy yaml's model_stage
-
-       def validate(self, request) -> str | None:
-           if not request.input or not request.input.strip():
-               return "Input text cannot be empty"
-           return None
-
-       async def build(self, request, sampling_params_list, has_inline_ref_audio):
-           params = {"text": [request.input]}
-           if request.voice is not None:
-               params["voice"] = [request.voice]
-           return PreparedRequest(
-               prompt={"prompt": request.input},
-               tts_params=params,
-               model_type=self.name,
-           )
+   _YOUR_MODEL_TTS_MODEL_STAGES = {"your_stage_key"}
   ```

-   Then add the module to the import block at the bottom of
-   `tts_adapters/__init__.py` so it registers. That import line is the only shared
-   file a new model touches — which is also why the old rebase-conflict hotspot is
-   gone.
+   **Point 2** — union into `_TTS_MODEL_STAGES`:
+   ```python
+   _TTS_MODEL_STAGES: set[str] = (
+       ...
+       | _YOUR_MODEL_TTS_MODEL_STAGES
+   )
+   ```

-   > **Pure-diffusion TTS does not go through adapters yet.** Under
-   > `for_diffusion()`, `create_speech()` routes straight to
-   > `_create_diffusion_speech()` and never calls `validate()`/`build()`.
-   > `DiffusionTTSAdapter` is scaffolding with no production subclass, so logic
-   > placed in one would silently never run. Diffusion-engine models follow the
-   > existing diffusion path; wiring it through adapters is open work (#4855).
+   **Point 3** — model type detection in `_detect_tts_model_type()`:
+   ```python
+   if model_stage in _YOUR_MODEL_TTS_MODEL_STAGES:
+       return "your_model"
+   ```

-   **If a stage key alone cannot identify the model**, declare
-   `model_archs = frozenset({"YourModelForConditionalGeneration"})`; add
-   `arch_identifies_entry_stage = True` when the model owns no stage key at all
-   (Ming dense). For a rule that is not set membership, override `matches()` (see
-   `covo_audio.py`). For a genuine overlap with another adapter, give one an
-   explicit `detect_priority` — `test_tts_detection.py` fails on an unordered
-   overlap. Models that only serve speech in some topologies override
-   `stage_serves_speech()` (see `audex.py`).
+   **Point 4** — validation dispatch in `_validate_tts_request()`:
+   ```python
+   if self._tts_model_type == "your_model":
+       return self._validate_your_model_request(request)
+   ```

-   **Reuse shared helpers via `self.ctx.server`** rather than reimplementing them:
-   `_resolve_ref_audio`, `_apply_uploaded_speaker`, `_validate_ref_audio_format`,
-   `_max_instructions_length`. Read a comparable adapter first — `fish_speech.py`
-   (voice cloning), `higgs_audio_v3.py` (parameter-heavy), `moss_tts.py` (family
-   sharing a base class).
+   **Point 5** — validation + parameter-builder methods:
+   ```python
+   def _validate_your_model_request(self, request) -> str | None:
+       if not request.input or not request.input.strip():
+           return "Input text cannot be empty"
+       return None

-   > **Do not add `self._tts_model_type == ...` branches to `serving_speech.py`.**
-   > Older models predate the adapter framework and still have them; they are being
-   > migrated out (RFC #4327, #4855). `tools/pre_commit/check_tts_adapter.py` is a
-   > ratchet on the remaining count and fails the commit if it grows. Behaviour that
-   > no adapter hook can express is a missing hook — propose it on the RFC.
+   def _build_your_model_params(self, request) -> dict:
+       params = {"text": [request.input]}
+       if request.voice is not None:
+           params["voice"] = [request.voice]
+       return params
+   ```
+   Wire `_build_your_model_params` into `_create_tts_request()` alongside the other
+   model-specific param builders.

-   > **Unused variable rule**: only extract fields in `build()` that are actually
-   > forwarded to the model. Unused extractions fail `ruff F841`. For voice-cloning
-   > fields (`ref_audio` -> `prompt_audio_path`, `ref_text` -> `prompt_text`), add
-   > them to the params and verify they reach the model call.
+   > **Two dispatch patterns coexist**: Fish Speech uses a `self._is_fish_speech` boolean
+   > instance attribute checked before `elif self._is_tts`, while all newer models
+   > (CosyVoice3, MOSS-TTS-Nano) use the `_tts_model_type` string returned by
+   > `_detect_tts_model_type()`. For new models, always use the `_tts_model_type` string
+   > pattern — do not add new `_is_*` flags.
+
+   > **Unused variable rule**: only extract fields in `_build_your_model_params` that
+   > are actually forwarded to the model. Unused extractions fail `ruff F841`.
+   > For voice-cloning fields (`ref_audio` → `prompt_audio_path`, `ref_text` →
+   > `prompt_text`), add them to the param builder and verify they reach the model call.
+
+   **Rebase conflict note**: when rebasing onto `main` after another model was merged,
+   `serving_speech.py` will conflict. Resolution: always keep *both* the upstream
+   model's additions and your own — never discard either side.

 2. **Handle model-specific parameters**:
   - Voice cloning: `ref_audio` encoding and prompt injection
@@ -300,7 +295,7 @@ import base64
 from pathlib import Path

 def build_voice_clone_prompt(ref_audio_path: str, text: str, codec) -> list:
-    """Build prompt with reference audio for voice cloning, called from the adapter."""
+    """Build prompt with reference audio for voice cloning in serving_speech.py."""
    audio_bytes = Path(ref_audio_path).read_bytes()
    codes = codec.encode(audio_bytes)  # Encode on CPU using model's codec (e.g., DAC)
    token_ids = [code + codec.vocab_offset for code in codes.flatten().tolist()]
@@ -326,7 +321,7 @@ Classify the model's **CI priority** first (high / medium / low). High-priority

 | Level | Location | Marker | CI pipeline | Notes |
 |-------|----------|--------|-------------|-------|
-| **L1** | `tests/model_executor/…`, `tests/entrypoints/openai_api/…`, stage-processor tests | `core_model` + `cpu` | `test-ready.yml` | Prompt assembly, async_chunk helpers, adapter validation — no GPU |
+| **L1** | `tests/model_executor/…`, `tests/entrypoints/openai_api/…`, stage-processor tests | `core_model` + `cpu` | `test-ready.yml` | Prompt assembly, async_chunk helpers, `serving_speech` validation — no GPU |
 | **L2** | `tests/e2e/online_serving/test_{slug}.py` | **`core_model` + `advanced_model`** (both on baseline smoke) + `tts` + `@hardware_test(...)` | `test-ready.yml` (`ready` label) | Default deploy smoke: single `/v1/audio/speech` or offline `OmniRunner` path |
 | **L3** | `tests/e2e/online_serving/test_{slug}.py` **and** `tests/e2e/offline_inference/test_{slug}.py` | Baseline smoke: **`core_model` + `advanced_model`**; heavier cases: `advanced_model` only (+ `tts`) | `test-merge.yml` **or** merged into nightly TTS function job | Streaming, voice clone, batch/queue, async_chunk |
 | **L4** | `tests/e2e/online_serving/test_{slug}_expansion.py`, optional offline expansion | `full_model` + `tts` | `test-nightly.yml` (`:full_moon: TTS · Function Test with L4`) | Feature matrix; perf → `tests/dfx/perf/tests/test_tts.json` |
@@ -371,7 +366,7 @@ See [vllm-omni-test skill](../vllm-omni-test/SKILL.md) § **Runtime send helpers

 ### Deliverables

- One adapter file under `tts_adapters/` plus its line in the package import block
+- Updated `serving_speech.py` with all 5 integration points (single commit)
 - Client scripts and server launcher under `examples/online_serving/text_to_speech/<model>/`
 - Gradio demo with streaming and voice cloning UI in the same dir
 - E2E tests per **Test Case Writing (CI Levels)** above (priority tier determines L1–L4 scope)
@@ -519,8 +514,8 @@ Use this checklist when integrating a new TTS model:
 - [ ] README.md written

 ### Phase 3: Online Serving
- [ ] Adapter written under `tts_adapters/` and registered in the import block
- [ ] Only extract params in `build()` that are forwarded to the model call (ruff F841)
+- [ ] All 5 `serving_speech.py` integration points added in one commit
+- [ ] Only extract params in `_build_*_params` that are forwarded to the model call (ruff F841)
 - [ ] Prompt builder handles text input correctly
 - [ ] Voice cloning works (if supported)
 - [ ] All response formats work (wav, mp3, flac, pcm)
@@ -1,231 +0,0 @@
---
-name: review-pr
-description: Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings. Use for default, detailed, or repeat maintainer reviews; checking correctness, compatibility, tests, benchmarks, model additions, distributed changes, or breaking behavior; and identifying or explicitly requesting the most relevant code-owner reviewers. Use precheck-pr instead for an author's pre-submit self-check.
---
-
-# Review vLLM-Omni Pull Requests
-
-Review like a maintainer: direct, selective, and focused on issues that CI does
-not prove. Prefer a few high-confidence findings over exhaustive commentary.
-Zero findings is a valid result.
-
-## Quality contract
-
-Make every finding:
-
- **Correct:** prove a reachable failure, not a suspicion.
- **Prioritized:** lead with merge blockers and high-impact defects.
- **Actionable:** identify the smallest safe fix direction.
- **Evidence-based:** cite code, tests, docs, CI, or measurements.
- **Concise:** avoid review templates and repeated summaries.
- **Calibrated:** match severity to user and maintainer impact.
-
-Do not report unrelated backlog, style already enforced by pre-commit, or a
-missing test that would not protect changed behavior.
-
-## Select the input and depth
-
-Use `vllm-project/vllm-omni` as the base repository. Accept its forks and local
-checkouts; use another skill for unrelated repositories.
-
-| Input | Review surface |
-| --- | --- |
-| PR number or URL | Frozen PR metadata, full diff, and relevant threads. |
-| Local branch/worktree | Frozen target-base SHA through committed, staged, unstaged, and in-scope untracked changes. |
-| Pre-filled context | Reuse supplied metadata; fetch only missing facts and the full diff. |
-
-Default to maintainer brevity. A detailed or audit request expands coverage and
-lists `path:line` findings, but keeps the same confidence and severity bar.
-
-## Reference guide
-
-Load references in review order: process, one primary module contract, matching
-feature designs, evidence checks, then delivery. Every file is linked directly
-below; do not load unrelated module references.
-
-Each concise reference links to the maintained
-[vLLM-Omni documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/).
-For branch-specific behavior, inspect the matching `docs/` file in the reviewed
-checkout first; use the published latest docs for current guidance and discovery.
-If docs and live code disagree, verify the code/tests and report the drift.
-
-### Review process
-
-| Reference | Read when |
-| --- | --- |
-| [review-execution.md](references/process/review-execution.md) | Every review; freeze inputs, inspect safely, and deliver against the same snapshot. |
-| [general-checks.md](references/process/general-checks.md) | Every review; apply repository-wide correctness and evidence rules. |
-| [design-contracts.md](references/process/design-contracts.md) | Every production review; resolve branch-local module and feature design status. |
-| [review-routing.md](references/process/review-routing.md) | After the diff census; select one primary module and conditional overlays. |
-
-### Primary module contract
-
-| Reference | Read when |
-| --- | --- |
-| [entrypoints.md](references/modules/entrypoints.md) | Offline/CLI/API ingress, validation, rendering, streaming, or sessions change. |
-| [configuration.md](references/modules/configuration.md) | Config construction, deploy/stage schema, defaults, registry, or topology changes. |
-| [input-output-modality.md](references/modules/input-output-modality.md) | Requests, messages, serialization, output types, accumulation, or completion change. |
-| [error-contracts.md](references/modules/error-contracts.md) | Error classification, fatality, propagation, sanitization, or rendering changes. |
-| [engine-orchestration.md](references/modules/engine-orchestration.md) | Cross-stage routing, request state, output ordering, RPC correlation, or terminal convergence changes. |
-| [stage-runtime.md](references/modules/stage-runtime.md) | Placement, startup, readiness, replica identity, affinity, membership, or shutdown changes. |
-| [omni-connector.md](references/modules/omni-connector.md) | Cross-stage/process/device/node transport or synchronization changes. |
-| [model-integration.md](references/modules/model-integration.md) | Registration, preprocessing, loading, runners, or model-specific execution changes. |
-| [ar-runtime.md](references/modules/ar-runtime.md) | AR scheduling, request/cache state, adapters, workers, or upstream vLLM semantics change. |
-| [diffusion.md](references/modules/diffusion.md) | Diffusion runtime, models, batching, parallelism, or offload changes. |
-| [execution-platforms.md](references/modules/execution-platforms.md) | Hardware selection, capabilities, vendor workers, kernels, or patches change. |
-| [cache-management.md](references/modules/cache-management.md) | Cache identity, reuse, validity, reset, eviction, or teardown changes. |
-| [quantization.md](references/modules/quantization.md) | Quantization selection, checkpoint metadata, layer mapping, precision, or constraints change. |
-| [observability.md](references/modules/observability.md) | Metrics, logs, units, labels, correlation, or lifecycle changes. |
-| [profiling.md](references/modules/profiling.md) | Profiling instrumentation, traces, start/stop lifecycle, or overhead changes. |
-| [benchmarking.md](references/modules/benchmarking.md) | Benchmark workload, metric calculation, CLI, or result metadata changes. |
-
-### Feature-design overlays
-
-| Reference | Read when |
-| --- | --- |
-| [runtime-stage-execution.md](references/features/runtime-stage-execution.md) | Disaggregated inference, async chunk/output/materialization, or prefix caching changes. |
-| [communication.md](references/features/communication.md) | A concrete OmniConnector backend or its deployment contract changes. |
-| [diffusion-acceleration.md](references/features/diffusion-acceleration.md) | Diffusion parallelism, attention, quantization, cache, batching, or offload changes. |
-| [infrastructure-performance.md](references/features/infrastructure-performance.md) | Metrics infrastructure or documented speech optimization stacks change. |
-
-### Evidence and quality checks
-
-| Reference | Read when |
-| --- | --- |
-| [model-addition-checklist.md](references/checks/model-addition-checklist.md) | A model, architecture, loader, processor, registry, or stage config is added. |
-| [perf-verification.md](references/checks/perf-verification.md) | The PR makes a latency, throughput, memory, or quality claim. |
-| [test-quality-evaluation.md](references/checks/test-quality-evaluation.md) | Tests change, are absent for risky code, or may not exercise production behavior. |
-| [tests-docs-checklist.md](references/checks/tests-docs-checklist.md) | Coverage, CI markers, examples, user docs, or PR evidence need review. |
-| [verification.md](references/checks/verification.md) | Hardware, a server, or a runnable affected path is available for active verification. |
-
-### Delivery and reviewer coordination
-
-| Reference | Read when |
-| --- | --- |
-| [maintainer-style-study.md](references/delivery/maintainer-style-study.md) | Findings are ready for concise maintainer-style delivery. |
-| [review-requests.md](references/delivery/review-requests.md) | The user asks to identify, suggest, request, or ping code-owner reviewers. |
-
-## Workflow
-
-### 1. Freeze and report the snapshot
-
-Pin the base and head before reading source or running validation. Within 60 seconds,
-report the pinned head, CI, mergeability, and preliminary findings in the host
-conversation. Do not wait for CI or post this update to GitHub.
-
-If the target changes while fetching, discard the evidence and retry once. If
-it changes again, report the churn and wait for a stable target.
-
-For a trusted PR head, materialize the pinned head in an isolated detached
-worktree. A worktree freezes identity but is not a security sandbox. Treat fork
-heads as untrusted unless the user and environment policy explicitly establish
-otherwise: execute them only in a disposable, secret-free sandbox with restricted
-filesystem, network, and resources; without one, use static SHA-addressed reads
-and CI evidence only. For a local review, freeze the committed, index, worktree,
-and NUL-safe in-scope untracked contents. Follow
-[review-execution.md](references/process/review-execution.md) for trust gates,
-state fingerprints, and byte-for-byte staleness checks.
-
-### 2. Build the diff census
-
-Group files into production code, tests, docs, configuration, build/CI, and
-generated artifacts. Map each changed production file and test group to the PR
-goal. Compare the title/body claims with the actual diff; use linked issues only
-when they define the contract or reproduction.
-
-Mark unrelated scope and unexplained generated artifacts. Do not infer behavior
-from the PR description without tracing the live code.
-
-### 3. Route from the live behavior
-
-Trace each claimed behavior through the changed producer to its live consumer,
-then use [design-contracts.md](references/process/design-contracts.md) and
-[review-routing.md](references/process/review-routing.md) to select one primary
-module contract, a second only for a real documented cross-boundary call path,
-and every matching feature-design and evidence overlay. Treat titles and paths
-as hints; live behavior and the frozen head's current design metadata are
-authoritative. For docs-, tests-, or CI-only changes, route to the production
-contract they protect or use only the applicable evidence checks.
-
-### 4. Run the blocker scan
-
-Apply every category in [general-checks.md](references/process/general-checks.md) before
-lower-priority comments.
-
-For each changed value or behavior, trace:
-
-```text
-public ingress -> validation/defaulting -> producer -> transformations
-  -> stage/worker/connector boundary -> final consumer -> terminal cleanup
-```
-
-Cover every applicable offline/online, streaming/non-streaming, sync/async,
-feature-on/off, topology, and compatibility path. Search bounded callers and
-sibling implementations rather than assuming the changed hunk is the only path.
-
-### 5. Apply module and feature contracts
-
-Apply the reference set selected in step 3 and any matching repo-local skill.
-Read the exact module and feature pages in the frozen head, including status,
-ownership boundary, dependencies, candidate invariants, safe-change guide, and
-promotion gate. Candidate or draft rules are questions, not blockers, unless
-current code, tests, or policy enforce them. Inspect both sides of any config,
-registry, serialization, connector, cache, or stage boundary.
-
-When a diff adds or expands a helper, class, fallback, compatibility branch, or
-public behavior, run a subtraction pass: remove out-of-scope behavior and check
-whether each new abstraction can be deleted, merged, moved, or inlined.
-
-### 6. Verify the changed path
-
-Before each validation group, verify the frozen SHA plus the tracked, index,
-untracked, and ignored-file fingerprint, or recreate a pristine snapshot. On a
-trusted head or inside the required sandbox, run an import/version preflight,
-then the narrowest relevant tests and low-cost static checks. Bind every result
-to the head SHA, snapshot fingerprint, and environment fingerprint. Never run
-imports, tests, builds, hooks, or repo-configurable tooling from an untrusted
-head on the reviewer host.
-
- Treat CI as status evidence; inspect only the first overlapping failure.
- For docs-only changes, use diff hygiene, links/build checks, and bounded live
-  contract verification instead of dependency setup or pytest.
- For hardware-dependent paths, run available static/CPU checks and name the
-  exact GPU/NPU gap. Never simulate device evidence.
- For performance or accuracy claims, require comparable base/head runs with
-  the same environment, workload, warmup, repetitions, and quality criteria.
-
-Stop when each changed semantic path has a supported finding or an explicit
-no-issue conclusion. Do not search further only to increase confidence.
-
-### 7. Consolidate and deliver
-
-Verify each finding against the current diff, deduplicate by root cause, and
-order by severity.
-
-Re-read the remote head and reverify or recreate the pristine validation
-snapshot immediately before delivery. If either changed, mark the review stale
-and restart from the new snapshot.
-
-Return findings first. Use
-[maintainer-style-study.md](references/delivery/maintainer-style-study.md) to keep them
-direct and brief. Each finding must include an exact `path:line`, trigger or
-call path, current behavior, impact, and smallest fix direction. If there are
-no findings, say so briefly and name material validation gaps.
-
-Keep the review read-only unless the user explicitly authorizes posting. Do not
-submit `APPROVE`, `COMMENT`, or `REQUEST_CHANGES`, add labels, edit code, or push
-commits as an implied part of review.
-
-### 8. Optionally request focused owner reviews
-
-Only when the user asks to identify or request reviewers, read
-[review-requests.md](references/delivery/review-requests.md). Rank path-matched
-CODEOWNERS with the frozen module page's owners or required reviewers and
-documented governance expertise; propose one to three focused reviewers with an
-explicit contract rationale.
-
-Identifying or suggesting reviewers is read-only. Requesting reviewers or
-posting `@mention` comments changes external state and requires explicit user
-authorization. When authorized, recheck the head, deduplicate existing
-requests, and post at most one consolidated comment. Do not infer this
-permission from a request to review the code.
@@ -1,4 +0,0 @@
-interface:
-  display_name: "vLLM-Omni PR Review"
-  short_description: "Review vLLM-Omni PRs and route owner requests"
-  default_prompt: "Use $review-pr to review this vLLM-Omni pull request with owner-specific rules and evidence-backed findings."
@@ -1,121 +0,0 @@
-# Model Addition Checklist
-
-Read this reference when a PR adds or expands a model architecture, pipeline,
-loader, processor, registry entry, or stage configuration.
-
-Official docs: [model contribution guides](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/),
-[adding an omni model](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/adding_omni_model/),
-[adding a diffusion model](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/adding_diffusion_model/),
-[adding a TTS model](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/adding_tts_model/),
-[supported models](https://docs.vllm.ai/projects/vllm-omni/en/latest/models/supported_models/),
-[diffusion features](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/diffusion_features/),
-and [feature compatibility](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/feature_compatibility/).
-
-## Match claims to the diff
-
- Reconcile every claimed architecture, modality, variant, feature, and example
-  with changed files and registry entries.
- Resolve config model types, architecture names, callable paths, exports, and
-  dependency extras against live symbols.
- Check sibling generations sharing an architecture name are disambiguated by
-  a stable config predicate rather than import order or an accidental default.
-
-## Close the integration chain
-
-Trace:
-
-```text
-public model id -> config/pipeline selection -> registry -> loader/processor
-  -> stage inputs -> model execution -> stage/public output
-```
-
-Verify optional dependencies fail with an actionable message, weight names and
-dtypes map correctly, and each advertised serving mode reaches the production
-dispatcher. Confirm outputs are non-empty and valid for their modality, shape,
-sample rate, or response schema.
-
-## Keep support documentation truthful
-
- Build an evidence-backed inventory of the new model's exact architecture and
-  checkpoint identifiers, modalities and tasks, hardware backends, serving
-  modes, and supported acceleration, parallelism, cache, offload, and
-  quantization features. Treat untested support as unknown, not supported.
- Update `docs/models/supported_models.md` with the architecture, model family,
-  example checkpoints, and only the backends validated by the PR.
- For a diffusion model, add it to the applicable ImageGen, VideoGen, or
-  AudioGen table in `docs/user_guide/diffusion_features.md`. Fill every feature
-  column according to its legend and document partial support or constraints.
- Update `docs/user_guide/feature_compatibility.md` when the model changes valid
-  feature combinations, configuration constraints, examples, or limitations,
-  and update any other branch-local support table affected by the claims.
- Cross-check every documented support mark against the registry, configuration,
-  production-path tests, and PR evidence; do not copy a sibling model's support
-  claims without validation.
-
-## Ship the model recipe
-
- Require every new model PR to add or update one model-family recipe under
-  `recipes/<vendor>/` and its row in the `recipes/README.md` Available Recipes
-  table. Follow [`recipes/TEMPLATE.md`](../../../../../recipes/TEMPLATE.md) and
-  the layout rules in
-  [`recipes/README.md`](../../../../../recipes/README.md); the
-  external recipes repository is a structural reference, not a substitute.
- Include only tested task, serving-mode, and hardware configurations. Keep the
-  exact model identifiers, flags, commands, verification, feature support,
-  constraints, and limitations consistent with code, tests, examples, and the
-  support documentation.
- Cover each validated platform in its own hardware section. Use one recipe per
-  model family by default; justify a split when configurations cannot be kept
-  clear in one file, and do not add placeholder sections for untested platforms.
-
-## Compare the reference implementation
-
-Require every new model PR to include a head-versus-reference accuracy or
-quality and performance comparison:
-
- Name the canonical implementation and pin its repository revision, package
-  version, configuration, and checkpoint. If it cannot run, explain why and use
-  the closest runnable reference; do not silently omit the comparison.
- Match inputs or dataset, seed, output settings, precision or quantization,
-  hardware, software, warmup, repetitions, synchronization, and timing and
-  memory scope. Include exact commands and environment details for both sides.
- Compare accuracy or output quality with a task-appropriate metric and explicit
-  tolerance. When no reliable metric exists, provide paired fixed-input outputs,
-  artifacts, and evaluation criteria, and explain expected numerical or
-  qualitative differences.
- Report end-to-end latency, task-appropriate throughput, peak device memory,
-  run-to-run variability, and head/reference ratios at equivalent output quality.
- Prefer a timing split for preprocessing or encoding, each model stage,
-  inter-stage transfer or communication, decoding or postprocessing, and output
-  assembly. Define the boundaries, account for overlap, reconcile the split with
-  end-to-end time, and explain any unavailable stage measurement.
-
-Use [perf-verification.md](perf-verification.md) for the comparison protocol and
-repository benchmark and profiling links.
-
-## Remove accidental surface
-
-Search bounded call sites for:
-
- inference-dead training `forward()` paths, unused factories/wrappers, never-set
-  branch keys, and immediately discarded parameters;
- duplicate payload strings, validation, or shape coercion across stages;
- compatibility aliases in brand-new code without an existing caller;
- private symbols re-exported as public API or module-level side effects.
-
-Keep code only when it has a distinct live caller, invariant, or compatibility
-contract. Prefer one typed producer-consumer schema to repeated string keys.
-
-## Require proportionate evidence
-
- Run a representative production-path inference and assert output content, not
-  only process survival.
- Require profiling or A/B tables when the PR makes performance, memory,
-  precision, or quality claims, or when a suspected hot-path/device bug needs
-  that evidence. Do not impose fixed utilization or regression thresholds that
-  the repository does not define.
- Require focused registry/config/loading tests, a representative E2E path, and
-  user-facing model/usage documentation.
-
-Use [diffusion.md](../modules/diffusion.md) for diffusion models and
-[perf-verification.md](perf-verification.md) for quantitative claims.
@@ -1,51 +0,0 @@
-# Performance and Accuracy Verification
-
-Activate this reference when the PR adds a model or claims or intentionally
-changes latency, throughput, memory, scaling, precision, or output quality.
-
-Official docs: [profiling](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/profiling/),
-[serving benchmarks](https://docs.vllm.ai/projects/vllm-omni/en/latest/cli/bench/serve/),
-and [metrics](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/metrics/).
-
-## Comparable A/B contract
-
-Compare frozen base and head for an existing path. For a new model absent from
-base, compare head with a pinned canonical reference implementation. Use the same:
-
- hardware, driver, software versions, model/checkpoint, and dependencies;
- input or dataset, seed, precision, batch/concurrency, topology, and feature
-  flags;
- warmup, measured repetitions, synchronization, timing scope, and memory
-  collection method.
-
-Keep exact commands and report variability rather than a cherry-picked run.
-Use the repository's benchmark when it covers the claim; otherwise use the
-smallest reproducible workload that reaches the changed production path.
-
-## Evidence table
-
-| Dimension | Typical evidence |
-| --- | --- |
-| Latency | End-to-end latency and, when available, TTFT plus a defined per-stage and transfer-time split. |
-| Throughput/scaling | Requests, tokens, frames, or audio duration per second across the claimed concurrency/topology. |
-| Memory | Peak allocated/reserved device memory and OOM boundary if relevant. |
-| Quality/accuracy | Repository metric or known-good output comparison with an explicit tolerance; paired samples when no metric exists. |
-
-Every optimization needs correctness or quality evidence. A faster result on a
-different workload, precision, seed, or topology is not a valid comparison.
-
-## Reviewer verification ladder
-
-1. Run base/head A/B on suitable hardware when affordable.
-2. If only one side can run, verify the script and request a comparable pair.
-3. If hardware or assets are unavailable, audit methodology, code path, and
-   contributor evidence; name the exact unverified claim.
-
-Classify discrepancies before reporting: implementation regression, benchmark
-bug, environmental drift, noise, or unsupported claim. Explain material
-regressions against the PR's stated goal or repository contract; do not invent
-universal percentage thresholds.
-
-Report claimed and measured values together, bind them to the frozen SHAs and
-environment, and keep unavailable hardware as a validation gap rather than a
-fabricated pass.
@@ -1,39 +0,0 @@
-# Test Quality Evaluation
-
-Read this reference when tests change, a risky production path has no test, or
-a test-only PR may not prove the intended behavior.
-
-Official docs: [test system overview](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_system_overview/)
-and [test writing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_writing_guide/).
-
-## Static proof check
-
-For each changed semantic path, ask whether the test would fail if that behavior
-were reverted or broken. Check:
-
- assertions pin the contract, not only non-null output, logs, or “no crash”;
- the production dispatcher, registry, connector, or scheduler is reached
-  instead of the changed behavior being mocked away;
- fakes preserve relevant types, MRO, shapes, devices, async behavior, and
-  lifecycle transitions;
- seeds, ordering, timing, synchronization, external services, and numeric
-  tolerances are deterministic or explicitly controlled;
- normal, invalid, boundary, feature-off, failure/cancellation, and regression
-  paths are covered where the diff changes them;
- run-level and domain markers place hardware/model tests in the intended CI
-  lane without silently skipping the contract.
-
-Map source symbols to tests with bounded `rg` searches; do not assume the test
-tree mirrors production paths.
-
-## Runtime check
-
-Run the narrowest affected tests supported by the environment. Record skipped
-hardware/model cases as gaps. Classify failures as code, test, infrastructure,
-or flaky before turning them into findings; one passing rerun does not erase a
-flakiness signal.
-
-Keep grades or matrices internal. Report only concrete code bugs or the one or
-two test defects that leave changed behavior materially unprotected. Use
-[tests-docs-checklist.md](tests-docs-checklist.md) for CI and documentation
-coverage.
@@ -1,48 +0,0 @@
-# Tests and Documentation Checklist
-
-Use this reference to connect changed behavior to coverage, CI selection,
-examples, documentation, and reproducible PR evidence.
-
-Official docs: [test writing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_writing_guide/),
-[test execution guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_execution_guide/),
-and [documentation guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/DOCS_GUIDE/).
-
-## Coverage packet
-
-For each high-risk change, record a compact internal packet:
-
-```text
-change and failure risk -> existing unit/E2E coverage -> uncovered boundary
-  -> smallest test and stable assertion that closes the gap
-```
-
-Prefer a regression test that fails on the frozen base for bug fixes. Check
-numeric tolerances, deterministic inputs, realistic mocks, hardware/domain
-markers, and Buildkite/CI wiring using the documentation present on the reviewed
-branch. A skipped test is not a pass.
-
-## Documentation sync
-
-Require user-facing updates when the diff changes a model, feature, CLI/API,
-config key, default, compatibility behavior, or supported platform. Verify:
-
- the actual docs navigation and support tables used by the branch;
- exact identifiers, defaults, constraints, known limitations, and migration;
- a minimal runnable example for newly exposed behavior;
- examples and docs agree on commands, parameters, output schema, and supported
-  modes;
- links and the bounded live contract build or resolve correctly.
-
-Do not request docs for internal behavior with no user-visible contract.
-
-## PR evidence
-
-For contributor-run tests or benchmarks, require enough provenance to evaluate
-the claim: hardware, relevant software versions, exact commands, inputs/model,
-result, and approximate runtime. Performance or accuracy evidence must compare
-base and head under equivalent conditions; use
-[perf-verification.md](perf-verification.md).
-
-Turn a missing test or document into a finding only when it protects or explains
-changed behavior. Name the smallest useful addition rather than requesting a
-broad coverage expansion.
@@ -1,36 +0,0 @@
-# Active Verification
-
-Read this reference when a runnable affected path and suitable local or remote
-hardware are available. Never claim device evidence from static analysis or a
-simulated backend.
-
-Official docs: [installation](https://docs.vllm.ai/projects/vllm-omni/en/latest/getting_started/installation/)
-and [test execution guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_execution_guide/).
-
-## Choose the narrowest level
-
-| Available environment | Verification |
-| --- | --- |
-| Matching accelerator, model/assets, and server | Targeted unit/integration test plus one representative E2E request. |
-| Matching accelerator without serving setup | Targeted model/runtime test and output or metric inspection. |
-| CPU/static environment only | Import/version preflight, focused CPU tests, config/registry resolution, and static contract checks. |
-| Missing dependencies or inaccessible hardware | Record the exact gap and evaluate contributor/CI evidence. |
-
-## Execute safely
-
-1. Bind the run to the frozen head SHA and record Python, platform, dependency,
-   model, device, and relevant environment fingerprints.
-2. Run the smallest affected unit test before an E2E workload.
-3. Exercise the changed public or production-dispatch path with bounded inputs.
-4. Compare actual output, metrics, cleanup, and exit behavior with the PR claim.
-5. For base/head claims, use the equivalent A/B protocol in
-   [perf-verification.md](perf-verification.md).
-
-Avoid disturbing shared servers, ports, models, or accelerators without user
-authorization. Do not install large dependencies, download gated assets, or
-start remote workloads merely because hardware might exist.
-
-Report the command, environment, result, and any skipped path. Classify failures
-as change-induced, pre-existing, infrastructure, environment, or flaky before
-making a finding. A hardware gap lowers confidence; it is not automatic proof
-of a defect.
@@ -1,105 +0,0 @@
-# Maintainer Review Style
-
-Use this reference only when turning proved findings into comments. The baseline
-maintainer samples favor short, direct comments and reserve long explanations
-for architecture or non-obvious failure paths.
-
-Official docs: [contributing and review process](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/).
-
-## Evidence basis
-
-This calibration used 928 PRs merged from 2026-05-10 through 2026-08-08.
-Candidates were ranked by substantive human inline-review threads, then by
-distinct reviewers and review rounds. Author self-comments, bots and AI
-reviewers, and bodyless approvals were excluded. Counts selected the sample;
-the practices below came from reading root comments and follow-up replies.
-
-The main set contains the six leaders after filtering; three other high-ranked
-PRs add core-runtime and benchmark coverage. All were merged.
-
-| PR | Review boundary |
-| --- | --- |
-| [#2906](https://github.com/vllm-project/vllm-omni/pull/2906) | New TTS model, shared utilities, recipes, and request state. |
-| [#3907](https://github.com/vllm-project/vllm-omni/pull/3907) | Full-duplex API, session lifecycle, concurrency, and realtime evidence. |
-| [#2162](https://github.com/vllm-project/vllm-omni/pull/2162) | Diffusion world model, OpenPI serving, tests, examples, and docs. |
-| [#3454](https://github.com/vllm-project/vllm-omni/pull/3454) | Diffusion model, generic CLI surface, loaders, and configuration scope. |
-| [#4425](https://github.com/vllm-project/vllm-omni/pull/4425) | Structured configuration, typing, defaults, and compatibility. |
-| [#5397](https://github.com/vllm-project/vllm-omni/pull/5397) | Distributed offload, collectives, failure handling, and load semantics. |
-| [#4281](https://github.com/vllm-project/vllm-omni/pull/4281) | Composable parallelism, configuration contracts, and examples. |
-| [#3628](https://github.com/vllm-project/vllm-omni/pull/3628) | Stage metrics, benchmark definitions, opt-in API behavior, and cleanup. |
-| [#3855](https://github.com/vllm-project/vllm-omni/pull/3855) | Stage runtime, thread safety, startup, and compatibility. |
-
-Historical comments calibrate delivery; they do not create merge policy. Live
-code, tests, repository docs, and the current `CODEOWNERS` file remain
-authoritative. When refreshing this study, promote a practice only when it
-recurs across at least three PRs or is supported by current repository guidance.
-
-## Recurring review behavior
-
- Start from a changed contract, not a style preference. State the exact
-  request, configuration, topology, or failure path that triggers the issue.
- Protect repository boundaries. Keep model-specific behavior in its domain,
-  move genuinely reusable logic to a shared module, and reuse existing loaders,
-  protocols, definitions, and config sources instead of bypassing them.
- Challenge unrelated scope and abstractions. Ask why a new flag, config, class,
-  helper, fallback, or file is needed when an existing path appears sufficient.
- Trace concurrency and terminal paths: overlapping requests, disconnect,
-  cancellation, partial failure, stale replies, collective schedule mismatch,
-  cleanup, and retry. Prefer an explicit startup error for unsupported
-  combinations over silently running with incomplete state or wrong weights.
- Preserve user-visible behavior across variants. An accepted CLI/API/config
-  field must be applied, explicitly rejected, or visibly warned about; compare
-  normal and headless, offline and online, and streaming and non-streaming paths.
- Ask for evidence at the affected boundary: a regression test using the real
-  tensor or protocol shape, correct pytest markers so CI runs it, comparable A/B
-  performance results, or an SLO-oriented latency/quality measurement.
- Keep interfaces explicit: avoid `Any` and opaque strings where a precise
-  union, enum, or typed envelope exists; remove dead code and duplicated
-  constants; validate requests before expensive execution.
- Document module scope and non-obvious invariants. Update examples, recipes,
-  supported-model/feature docs, and hardware assumptions when users rely on
-  them.
- When expertise crosses an ownership boundary, ask a named owner to inspect a
-  specific file or contract and explain why. Do not send a generic `PTAL` list.
- Keep non-blocking cleanup in a linked follow-up only after the current PR is
-  safe. If a revision fixes only part of a failure chain, continue the existing
-  thread with the remaining trigger instead of opening a duplicate finding.
-
-## Write the finding
-
- Lead with the issue or decisive question; omit a review preamble.
- Name the concrete trigger and impact, then the smallest fix direction.
- Keep obvious fixes to one sentence. Use more detail only when the call path or
-  ownership boundary is otherwise unclear.
- Prefer one root-cause comment over repeated symptom comments.
- Hedge only when evidence is genuinely incomplete; mark that item as a
-  question or validation gap rather than overstating severity.
- Say briefly that no findings were found when the review is clean; zero
-  comments is a valid outcome when posting is authorized.
-
-Useful forms:
-
-```text
-This leaves <state> allocated when <failure/cancellation path>. Release it in
-the shared terminal cleanup path.
-```
-
-```text
-Does this producer also update <consumer>? It still reads the old field here.
-```
-
-```text
-With <configuration>, this bypasses <existing loader/validator>, so <impact>.
-Reuse that path or reject this combination before startup.
-```
-
-```text
-@<owner>, could you check <specific boundary>? This changes <contract> used by
-<consumer>.
-```
-
-Use a priority label only for a proved high-impact defect. Avoid generic praise,
-routine “Nit:” prefixes, decorative severity labels, audit templates, rule IDs,
-comment-count narration, and “I left a few comments.” Keep approvals, review
-events, reviewer requests, mentions, and GitHub replies subject to the user's
-explicit authorization.
@@ -1,99 +0,0 @@
-# Focused Code-Owner Review Requests
-
-Read only when the user asks to identify, suggest, request, add, or ping
-reviewers. Finding candidates is read-only; GitHub review requests and
-`@mention` comments are external writes.
-
-Owner sources, in order:
-
-1. the reviewed head's
-   [CODEOWNERS](https://github.com/vllm-project/vllm-omni/blob/main/.github/CODEOWNERS)
-   for path ownership;
-2. the active module design page's `owners` and `required_reviewers` metadata
-   for contract ownership and mandatory design review; and
-3. documented
-   [governance expertise](https://docs.vllm.ai/projects/vllm-omni/en/latest/community/governance/)
-   for specialization and tie-breaking.
-
-Resolve all three from the reviewed head when available because ownership
-changes over time. Use published docs only to discover a page absent from an
-older checkout, never to override the frozen head, and do not copy a static
-owner list into review output. CODEOWNERS remains the path authority; module
-metadata identifies contract experts and required design reviewers.
-
-## Rank candidates
-
-1. Freeze the PR head and collect changed files, author, requested reviewers,
-   submitted reviews, and existing comments.
-2. Resolve the **last matching CODEOWNERS rule** for each changed file. Do not
-   union an earlier broad rule with a later specific rule.
-3. Resolve the primary module and feature overlays through
-   [design-contracts.md](../process/design-contracts.md). Read the active module
-   page's status, `owners`, and `required_reviewers`; do not treat owners on an
-   archived, superseded, or unrelated page as current authority.
-4. Group files by the selected primary owner and the exact module or feature
-   contract needing review. Weight production owners and live consumers above
-   tests/docs/CI owners and the repository-wide fallback. Include an applicable
-   `required_reviewers` entry even when it is not the path owner, and label why.
-5. Use documented governance specialties only to choose among matching owners:
-   for example serving versus configuration, diffusion model versus cache or
-   parallelism, TTS versus generic model execution, or CI versus tests.
-6. Exclude the PR author, bots, users who already completed the needed review,
-   and duplicate pending requests. Do not infer availability or invent
-   expertise from a username.
-7. Select one reviewer for a single-owner change and at most three for a real
-   cross-module change. If more are plausible, rank them but do not ping a
-   broad group; ask the user before exceeding three.
-
-If every specific owner is excluded, consider one repository-wide fallback
-owner and label that choice as a fallback rather than a path match. Never fan
-out to the full fallback list. Prefer a qualified owner who covers multiple
-critical path groups over separate reviewers for each file. If CODEOWNERS is
-missing or invalid, state that gap and use governance only as a labeled fallback.
-
-Recent file history may break a tie only when CODEOWNERS and governance remain
-ambiguous. Never use commit count alone to override an explicit current owner.
-
-## Preview before writing
-
-Show the user the exact candidate set and rationale:
-
-```text
-@owner — <owned paths or module role>; please verify <specific module or feature contract>.
-```
-
-Draft one consolidated comment tied to the frozen head:
-
-```text
-Requesting focused review for `<short-head-sha>`:
-
- @owner1: could you check the <module contract> in `<path/group>`?
- @owner2: could you check the <feature or cross-boundary contract> in `<path/group>`?
-
-Relevant validation: <one concise result or exact remaining gap>.
-```
-
-Mention only owners being requested. Keep the reason specific enough that each
-person knows what decision or invariant needs attention; do not post a generic
-“please review” or a generated ownership audit.
-
-## External-write gate
-
- “Who should review?”, “suggest reviewers”, or “draft a request” authorizes
-  only the preview.
- “Request/add these reviewers” authorizes the GitHub review-request mutation.
- “Ping/comment/tag the owners” authorizes the consolidated comment.
- When the user explicitly asks to request reviews **with an owner comment**,
-  both writes are authorized. Obey narrower wording when only one action is
-  requested.
-
-Immediately before an authorized write, verify the PR is still open, the head
-SHA is unchanged, and the candidate is not the author or already satisfied.
-Report draft/WIP state and avoid notifications unless the user explicitly wants
-reviewers requested before ready-for-review.
-
-Use the GitHub connector for reviewer requests and the single top-level comment;
-use `gh` only when connector coverage is unavailable. Do not submit an approval,
-request-changes event, label, assignment, or multiple comments as part of this
-action. After writing, reread the PR and report the reviewers requested and the
-comment URL. If the head changed, discard the draft and rerank before posting.
@@ -1,24 +0,0 @@
-# Communication Features
-
-Use with the OmniConnector, stage-runtime, configuration, and I/O module
-contracts. Load the concrete backend design from the reviewed head:
-
-| Backend | Design |
-| --- | --- |
-| Mooncake store | [MooncakeStoreConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/mooncake_store_connector/) |
-| Mooncake transfer engine | [MooncakeTransferEngineConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/mooncake_transfer_engine_connector/) |
-| Mori transfer engine | [MoriTransferEngineConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/mori_transfer_engine_connector/) |
-| Shared memory | [SharedMemoryConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/shared_memory_connector/) |
-| Yuanrong store | [YuanrongConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/yuanrong_connector/) |
-| Yuanrong transfer engine | [YuanrongTransferEngineConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/yuanrong_transfer_engine_connector/) |
-
-## Feature checks
-
- Verify dependency, service, device/network, port, memory-pool, and environment
-  prerequisites with actionable startup errors.
- Match key/metadata construction, sender and receiver roles, allocation,
-  ownership, completion, and supported fast/serialized paths.
- Exercise timeout, retry, stale sender/buffer reclamation, partial transfer,
-  cancellation, and connector close semantics.
- Validate the smallest supported same-host or cross-node topology and document
-  backend limitations and operational diagnostics.
@@ -1,26 +0,0 @@
-# Diffusion Acceleration Features
-
-Use with the exact diffusion submodule plus platform, cache, quantization, or
-benchmarking contracts selected by the live path.
-
-| Feature family | Designs |
-| --- | --- |
-| Parallelism | [CFG](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/cfg_parallel/), [Expert](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/expert_parallel/), [HSDP](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/hsdp/), [Pipeline](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/pipeline_parallel/), [Sequence](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/sequence_parallel/), [Tensor](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/tensor_parallel/), [VAE patch](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/vae_parallel/) |
-| Attention | [Skip-Softmax](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/skip_softmax/) |
-| Quantization | [Quantization](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/quantization/) |
-| Cache | [Cache-DiT](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/cache_dit/), [TeaCache](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/teacache/) |
-| Batching | [Diffusion Continuous Batching](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/diffusion_continuous_batching/) |
-| Offload | [Distributed Layerwise Offload](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/distributed_layerwise_offload/) |
-
-## Feature checks
-
- Verify feature selection, supported models/platforms/topologies, defaults,
-  dependencies, and every touched feature combination.
- Preserve feature-off and single-rank correctness; reject unsupported
-  combinations before collectives, loading, or execution begin.
- Trace shapes, shards, ranks, collectives, precision, cache validity, residency,
-  and per-request state through the selected runtime hooks.
- Compare output quality or accuracy against the disabled/reference path before
-  accepting latency or memory improvements.
- Require exact commands, topology, environment, warmup, repetitions, and
-  measurements for performance claims; update feature compatibility docs.
@@ -1,22 +0,0 @@
-# Infrastructure and Performance Features
-
-Load the matching design from the reviewed head:
-
- [Prometheus Metrics](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/metrics/)
-  for logger wrapping, gating, lifecycle, stage transfer, and metric definitions.
- [Speech Generation Performance Optimizations](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/qwen3_omni_tts_performance_optimization/)
-  for stage batching, CUDA graphs, async chunk, streaming, re-prefill, compile,
-  and deployment evidence.
-
-## Feature checks
-
- Route instrumentation changes through observability or profiling and result
-  methodology through benchmarking and the performance evidence check.
- Preserve opt-in/default behavior, units, labels, aggregation, timing scope,
-  lifecycle resets, and bounded overhead.
- For stacked optimizations, measure each increment against the same baseline
-  and explain interactions, quality guards, regressions, and limitations.
- Require exact model, checkpoint, hardware, software, workload, topology,
-  concurrency, warmup, repetitions, and production commands.
- Update the design page when metric meaning, supported optimization stack, or
-  deployment guidance changes.
@@ -1,24 +0,0 @@
-# Runtime and Stage Execution Features
-
-Load the matching design from the reviewed head:
-
-| Feature | Design | Primary module intersections |
-| --- | --- | --- |
-| Disaggregated inference | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/disaggregated_inference/) | Configuration, stage runtime, OmniConnector, I/O contracts |
-| Async chunk | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/async_chunk/) | Model integration, orchestration, stage runtime, connector, I/O |
-| Async diffusion output | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/async_diffusion_output/) | Diffusion runtime, I/O contracts, entrypoints |
-| Async Omni output materialization | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_async_output_materialization/) | AR runtime, model integration, I/O contracts, orchestration |
-| Automatic prefix caching | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/prefix_caching/) | AR runtime, cache management, I/O contracts |
-
-## Feature checks
-
- Confirm the feature's supported models, entrypoints, stage types, topology,
-  configuration, default, and compatibility limitations.
- Trace enablement from public/config ingress through every participating module
-  and verify the advertised production dispatch actually selects it.
- Preserve a correct disabled or fallback path and make unsupported combinations
-  fail or warn as documented.
- Test overlap, ordering, identity, backpressure, cancellation, failure, final
-  partial output, and cleanup at each asynchronous boundary.
- Update the feature page, support matrices, examples, and recipes when behavior
-  or coverage changes.
@@ -1,22 +0,0 @@
-# Autoregressive Runtime
-
-Primary design: [Autoregressive Runtime](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/ar_runtime/).
-
-Use for AR request queues, scheduling state, token and memory budgets, KV/input
-readiness, workers, runners, and upstream vLLM request/cache transitions.
-
-## Contract checks
-
- Preserve upstream request-state, scheduling, cache, and preemption semantics
-  unless an Omni-specific difference is documented and tested.
- Convert modality-specific data through explicit input or output adapters; do
-  not inject it through unrelated scheduler state.
- Keep workers and model runners focused on assigned execution rather than
-  admission or cross-stage routing.
- Synchronize token, sequence, batch, and memory budgets with worker-visible
-  state and prevent starvation, double counting, or stale readiness.
- Preserve legal transitions and one terminal cleanup path across completion,
-  abort, timeout, preemption, worker failure, and shutdown.
-
-Test request lifecycle, scheduling decisions, abort, cache state, adapters, and
-every affected worker execution mode against the pinned upstream contract.
@@ -1,24 +0,0 @@
-# Benchmarking
-
-Primary design: [Benchmarking](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/benchmarking/).
-
-Use when benchmark code, workloads, metric calculations, CLI benchmark
-entrypoints, or result metadata change. Use the performance check separately
-when a PR uses benchmark results as evidence.
-
-## Contract checks
-
- Record model and revision, code SHA, hardware, software, configuration,
-  workload, precision, topology, concurrency, warmup, repetitions, and
-  measurement window.
- Validate successful and semantically acceptable outputs before accepting
-  timing, memory, or scaling results.
- Define every metric's unit, population, aggregation, synchronization, and
-  timing scope.
- Keep workload parsing and metric computation deterministic and reusable
-  across base and head.
- Reject comparisons that change material workload or runtime settings without
-  isolating and explaining that difference.
-
-Test workload parsing and metric calculations with deterministic fixtures and
-publish exact commands plus variability for quantitative claims.
@@ -1,22 +0,0 @@
-# Cache Management
-
-Primary design: [Cache Management](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/cache_management/).
-
-Use for AR or diffusion cache identity, reusable state, validity, lifecycle,
-reset, eviction, and teardown.
-
-## Contract checks
-
- Include every model, request, input, timestep, precision, device, topology,
-  and feature property that can change a reused value in cache identity.
- Preserve a correct disabled and miss path; never reuse after validity inputs
-  change.
- Isolate request-scoped state across concurrent requests and define ownership
-  for model-scoped state.
- Make reset, invalidation, eviction, capacity, and teardown explicit on
-  completion, cancellation, failure, model reload, and shutdown.
- Keep cache optimizations behind the owning runtime's hooks rather than adding
-  a second request lifecycle.
-
-Test hit, miss, invalidation, disabled behavior, concurrency, capacity, reset,
-and teardown, with quality comparison when reuse is approximate.
@@ -1,24 +0,0 @@
-# vLLM-Omni Configuration
-
-Primary design: [vLLM-Omni Configuration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/vllm_omni_config/).
-
-Use for config construction, deploy YAML, registries, schema, defaults,
-aliases, CLI projection, stage config, and topology. Inspect the reviewed
-page's status: while its contract remains deferred or draft, current code and
-tests—not proposed precedence rules—are authoritative.
-
-## Contract checks
-
- Resolve each supported structured, legacy, CLI, environment, default, alias,
-  and stage-override producer through its actual runtime consumer.
- Reject unknown or owner-mismatched fields explicitly; keep process-local
-  runtime objects out of transportable configuration.
- Verify default, explicit, and feature-off values reach every live factory and
-  consumer without silent reinterpretation.
- Treat stage count, placement, connector, parallelism, device, and memory
-  fields as one topology contract and reject impossible combinations early.
- Preserve supported construction-path parity until a documented migration
-  removes a path.
-
-Require normalization and schema tests, a live-consumer assertion, and docs for
-public keys, defaults, constraints, precedence, or migration behavior.
@@ -1,33 +0,0 @@
-# Diffusion Module Family
-
-Primary design: [Diffusion Modules](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/).
-
-Use for diffusion-stage behavior, then load the exact submodule page from the
-reviewed head:
-
-| Submodule | Signals | Design |
-| --- | --- | --- |
-| Runtime | Admission, scheduling, execution, progress, outputs, cancellation, hooks, cleanup | [Diffusion Runtime](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/diffusion_runtime/) |
-| Model Integration | Pipelines, registry, loader, adapters, shared layers, model-specific processing | [Diffusion Model Integration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/diffusion_model_integration/) |
-| Continuous Batching | Compatibility, request/step batches, per-request progress, capacity | [Continuous Batching](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/continuous_batching/) |
-| Parallelism | Rank topology, process groups, sharding, collectives, distributed execution | [Parallelism](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/parallelism/) |
-| Offloader | Residency, transfers, memory accounting, prefetch, teardown | [Offloader](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/offloader/) |
-
-## Family-wide checks
-
- Keep one scheduler-owned lifecycle from admission through completion,
-  cancellation, failure, and cleanup; optional features must use defined hooks.
- Select pipelines through registry and loader contracts instead of scattered
-  model-name conditionals; keep genuine model differences in model directories.
- Trace latent, conditioning, timestep, generator, shape, layout, dtype, device,
-  batch expansion, and output conversion through the actual consumer.
- Make batch compatibility and per-request isolation explicit; never associate
-  output by unstable batch position.
- Derive topology from validated configuration, define every sharding boundary,
-  keep collectives symmetric, and preserve a supported single-rank path.
- Track one residency owner per offloaded component, wait for transfer readiness,
-  preserve model state, bound retained copies, and clean up deterministically.
-
-Load matching feature designs for cache, quantization, parallelism, continuous
-batching, or offload. Require feature-off correctness, representative inference,
-terminal-path tests, and quality evidence for optimizations.
@@ -1,23 +0,0 @@
-# Engine Orchestration
-
-Primary design: [Engine Orchestration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/engine_orchestration/).
-
-Use for request-state creation, cross-stage routing, output ordering, companion
-tracking, RPC correlation, cancellation propagation, and terminal convergence.
-Orchestration does not own replica placement, stage-process startup, public
-rendering, connector transport, or payload and error schemas.
-
-## Contract checks
-
- Keep one owner for cross-stage routing; entrypoints, models, and stage clients
-  must not independently select the next logical stage.
- Preserve request identity and output order across concurrent stages and
-  correlate every control or RPC result to the originating request and wave.
- Make terminal state monotonic: no new forwarding after success, abort,
-  request failure, or fatal engine failure.
- Propagate cancellation and failure to every active stage and release
-  orchestrator-owned tasks, queues, companions, and request state.
- Preserve shutdown ordering across the orchestrator and stage runtime.
-
-Test representative multi-stage routing, ordering, correlation, cancellation,
-failure, and repeated shutdown.
@@ -1,25 +0,0 @@
-# Entrypoints and Serving Boundaries
-
-Primary design: [Entrypoints and Serving Boundaries](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/entrypoints/).
-
-Use for offline APIs, CLI and server composition, OpenAI-compatible routes,
-request validation, response conversion, streaming, sessions, and engine
-handoff. Entrypoints adapt public contracts; they do not own cross-stage
-routing, stage lifecycle, configuration precedence, payload schemas, or error
-classification.
-
-## Contract checks
-
- Normalize and validate public values once before engine submission.
- Preserve request identity, modality, ordering, and exactly one terminal event
-  across streaming, disconnect, cancellation, and failure.
- Translate internal outputs and errors explicitly for each advertised offline,
-  HTTP, SSE, WebSocket, or asynchronous-job path.
- Keep model-specific behavior behind a common adapter or processor instead of
-  adding model-name policy to generic entrypoints.
- Require API or CLI changes to explain necessity, alternatives, compatibility,
-  migration, and the supported route or transport matrix.
-
-Test the affected public protocol, normalization, engine handoff, rendering,
-and terminal outcomes. Route orchestration, I/O schema, and semantic error
-changes to their module contracts.
@@ -1,24 +0,0 @@
-# Error Classification, Propagation, and Rendering
-
-Primary design: [Error Classification, Propagation, and Rendering](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/error_contracts/).
-
-Use when a change classifies failures, crosses process boundaries, decides
-fatal versus request-scoped impact, sanitizes context, or renders offline,
-HTTP, SSE, WebSocket, or asynchronous-job errors. The I/O module owns the wire
-schema; this module owns the meaning of its error fields.
-
-## Contract checks
-
- Keep request-scoped failure isolated unless the underlying engine is no
-  longer usable.
- Preserve stable classification and request context across process and
-  protocol boundaries without exposing prompts, outputs, secrets, or internal
-  stack details.
- Keep cancellation distinguishable from internal failure.
- Terminate each public transport exactly once with consistent status, body,
-  event, finish reason, and metrics classification.
- Maintain compatibility across mixed or older producers only when the
-  reviewed contract defines that behavior.
-
-Test table-driven classification, wire round trips, fatal/request-scoped
-propagation, cancellation, sanitization, and every affected public renderer.
@@ -1,23 +0,0 @@
-# Execution Platforms
-
-Primary design: [Execution Platforms](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/execution_platforms/).
-
-Use for hardware capability detection, worker selection, patches, kernels,
-attention backends, and vendor-specific configuration or connectors.
-
-## Contract checks
-
- Guard hardware behavior through platform selection or capability detection
-  and fail clearly when unsupported.
- Keep portable modules free of direct vendor imports when a common selector
-  exists; verify portable imports without the target accelerator.
- Override only behavior that differs from common or upstream implementations,
-  and compare sibling worker hooks when inheritance does not provide parity.
- Preserve dtype, layout, rank, stream, synchronization, workspace,
-  graph-capture, and resource-lifetime contracts.
- Do not let simplified CPU doubles hide platform MRO, initialization, or
-  dispatch failures.
-
-Run portable checks first, then the smallest matching-device test in a fresh
-environment. Report unavailable hardware as a validation gap, never simulated
-device evidence.
@@ -1,23 +0,0 @@
-# Input, Output, and Modality Contracts
-
-Primary design: [Input, Output, and Modality Contracts](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/input_output_modality_contracts/).
-
-Use for requests, prompt and modality types, message schemas, serialization,
-output types, accumulation, completion, and compatibility shims crossing
-entrypoint, orchestration, stage, connector, or model boundaries.
-
-## Contract checks
-
- Give every boundary value an explicit modality and validated typed schema.
- Preserve request and stage identity across conversion, serialization,
-  streaming updates, batching, cancellation, and errors.
- Distinguish partial, final, empty, and failed output states for every modality.
- Verify producer and consumer agreement on shape, layout, dtype, device,
-  ownership, metadata, ordering, and optional or unknown fields.
- Keep internal objects out of public protocols; translate them at the owning
-  entrypoint.
- Preserve wire compatibility deliberately and give deprecated shims a bounded
-  migration path.
-
-Require construction, round-trip, accumulation, completion, rejection, and
-compatibility tests at each changed producer-consumer boundary.
@@ -1,25 +0,0 @@
-# Model Integration
-
-Primary design: [Model Integration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/model_integration/).
-
-Use for model registration, configuration adapters, preprocessing, checkpoint
-loading, stage inputs, model-specific hooks, shared layers, runners, and model
-execution. Use the diffusion family reference for diffusion models.
-
-## Contract checks
-
- Declare explicitly how the model class, loader, input processor, stage
-  configuration, and runtime capabilities are selected.
- Preserve weight-name mapping, dtype/device placement, optional-dependency
-  errors, and checkpoint-specific loading semantics.
- Trace each typed input and output through preprocessing, runner state, model
-  call, and its actual consumer.
- Reuse upstream vLLM behavior when sufficient; document and test the precise
-  difference for every override or patch.
- Keep model code out of admission, cross-stage routing, public policy, and
-  terminal lifecycle ownership.
- Place reusable behavior in shared modules and test it with more than one
-  integration.
-
-Require focused registry, loader, processor, runner, and representative model
-execution tests. Apply the model-addition check for new or expanded support.
@@ -1,21 +0,0 @@
-# Observability
-
-Primary design: [Observability](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/observability/).
-
-Use for metrics, logs, correlation fields, and cross-stage request visibility.
-
-## Contract checks
-
- Preserve stable request and stage identity across entrypoints, orchestration,
-  stages, workers, errors, and terminal cleanup.
- Treat metric names, units, labels, aggregation, and lifecycle as public
-  contracts; document any semantic change.
- Keep labels bounded: never use request IDs, prompts, outputs, paths, or other
-  unbounded user values.
- Register and reset metrics exactly once across repeated startup and shutdown,
-  and keep disabled instrumentation inexpensive.
- Align emitted values with their actual timing and lifecycle owner rather than
-  reconstructing them from ambiguous client strings.
-
-Test registration, label sets, units, resets, error classification, and
-representative multi-stage emission.
@@ -1,24 +0,0 @@
-# OmniConnector
-
-Primary design: [OmniConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/omni_connector/).
-
-Use for connector contracts and model-agnostic data transfer across stages,
-processes, devices, or nodes. Connector implementations transport and
-synchronize data; they do not choose the next stage or implement model policy.
-
-## Contract checks
-
- Prove producer and consumer agreement on request/stage identity, shape,
-  layout, dtype, placement, ownership, ordering, and completion.
- Keep backend selection and metadata/key construction explicit; do not silently
-  reinterpret or drop payloads across SHM, store, network, or vendor paths.
- Bound connect, put/get, retry, synchronization, and readiness waits with
-  backpressure, cancellation, and actionable errors.
- Prevent route, endpoint, port, key, and buffer collisions across repeated
-  startup, concurrent requests, and replica replacement.
- Release connections, handles, buffers, listener work, and stale sender state
-  on success, cancellation, failure, and shutdown.
-
-Load the matching communication feature design for a concrete backend. Require
-focused producer-consumer tests and the smallest runnable multi-process or
-multi-node path.
@@ -1,21 +0,0 @@
-# Profiling
-
-Primary design: [Profiling](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/profiling/).
-
-Use for opt-in instrumentation and trace collection across supported profiler
-backends.
-
-## Contract checks
-
- Keep expensive collection disabled by default and bounded by explicit start,
-  stop, timeout, and cleanup behavior.
- Preserve scheduling, generated outputs, resource ownership, and concurrency
-  semantics apart from documented synchronization overhead.
- Include stage, rank, worker, operation, and request correlation where useful
-  without embedding user payloads or secrets.
- Make repeated start/stop and partial failure safe, including multi-rank trace
-  naming and artifact ownership.
- Measure disabled and enabled overhead before making performance claims.
-
-Test the disabled path, repeated lifecycle, failure cleanup, trace context, and
-each affected backend.
@@ -1,22 +0,0 @@
-# Quantization
-
-Primary design: [Quantization](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/quantization/).
-
-Use for method registration, checkpoint interpretation, layer replacement,
-reduced precision, platform capability, and runtime constraints.
-
-## Contract checks
-
- Validate checkpoint metadata, selected method, supported layers, device
-  capability, required dependencies, and parallel layout before loading.
- Preserve loader and weight-name mapping semantics, dtype, scale/granularity,
-  zero point, padding, and buffer handling through the real kernel consumer.
- Fail clearly for unsupported combinations; do not silently choose a different
-  method or precision.
- Keep online and pre-quantized checkpoint paths explicit and ensure patches or
-  fallbacks do not bypass model-owned loaders.
- Require numerical comparison against a defined reference with explicit
-  tolerance before treating performance results as valid.
-
-Test registration, loading, representative layers, metadata, platform guards,
-parallel combinations, and numerical correctness separately from performance.
@@ -1,23 +0,0 @@
-# Stage Runtime and Replica Lifecycle
-
-Primary design: [Stage Runtime and Replica Lifecycle](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/stage_runtime/).
-
-Use for local or distributed placement, startup, readiness, stage pools,
-replica identity and membership, selection, affinity, liveness, draining, and
-stage-client or process lifecycle. Cross-stage request policy belongs to engine
-orchestration; model scheduling belongs to the owning runtime.
-
-## Contract checks
-
- Acquire, replace, and retire replicas through one stage-runtime lifecycle.
- Preserve stable replica identity and request affinity until termination or a
-  declared replica loss.
- Make readiness explicit before admission; surface partial-startup and
-  membership failures without leaving half-initialized capacity.
- Keep local and distributed semantics aligned for supported modes.
- Make drain, shutdown, and cleanup idempotent across repeated signals and
-  process failure.
-
-Test startup, readiness, selection, affinity, membership changes, abort,
-process loss, draining, and repeated shutdown on affected local/distributed
-paths.
@@ -1,34 +0,0 @@
-# Resolve Design Contracts
-
-Use after freezing the review head and before selecting module or feature
-references. The maintained [design index](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/)
-defines two routing axes:
-
- **Module designs** own code boundaries and invariants. Select one primary
-  module and a second only when the live producer-consumer path crosses it.
- **Feature designs** describe behavior spanning modules. Load every feature
-  page whose implementation, default, support, or contract changes.
-
-## Resolution order
-
-1. Open `docs/design/index.md` in the reviewed head, not the reviewer's checkout
-   or published latest tree.
-2. Match changed behavior against each module page's `primary_code_paths`,
-   `primary_path_exceptions`, ownership boundary, and `depends_on` metadata.
-3. Read `status`, `architecture_state`, `last_verified_commit`, and any linked
-   in-flight work before treating prose as current behavior.
-4. Use current code and tests when a page is draft, deferred, stale, absent, or
-   conflicts with the frozen implementation. Report material documentation
-   drift separately.
-5. Treat candidate invariants and promotion gates as review questions until
-   repository policy, current code/tests, or owner-approved normative text
-   makes them enforceable. Do not turn a draft identifier into an automatic
-   blocker.
-6. Use published latest docs only for discovery when the reviewed head lacks a
-   page; never import a newer contract into an older branch silently.
-
-When behavior changes an active module or feature contract, require the same PR
-to update that page. Require a new page only when repository policy, an accepted
-RFC/issue, or explicit maintainer acceptance criteria do so; otherwise treat it
-as a non-blocking design suggestion. Do not demand a second page when an existing
-design already owns the exact contract.
@@ -1,129 +0,0 @@
-# General Review Checks
-
-Apply these checks to every PR after freezing the review surface. A pattern is
-not a finding until the diff introduces or exposes a reachable trigger, impact,
-and smallest safe fix. Do not report unrelated backlog.
-
-Official docs: [contributing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/)
-[feature compatibility](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/feature_compatibility/),
-and [design documents](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/).
-
-## Contract and scope
-
- Match the title/body claims to every changed production path, test, config,
-  dependency, generated artifact, and user-visible document.
- Trace each changed value through public ingress, validation/defaulting,
-  producer, transformations, process or device boundaries, final consumer, and
-  terminal cleanup.
- Check every applicable sync/async, offline/online, streaming/non-streaming,
-  feature-off, topology, and compatibility path without demanding unsupported
-  modes merely for symmetry.
-
-## Module, API, and class design
-
-Apply these rules to new or materially changed production code; do not require
-unrelated cleanup from untouched files.
-
-1. Start each source module with a concise module docstring that defines its
-   responsibility and boundaries and identifies its primary classes and key
-   functions. Place it after any required license header and before imports.
-2. Give every added or materially changed class and function a clear docstring
-   covering its responsibility, parameters, return value, raised exceptions,
-   and non-obvious invariants. Use explicit typed parameters at owned API
-   boundaries; avoid opaque `**kwargs` and `Any`. Allow them only when an
-   upstream or compatibility interface requires them, and document and validate
-   the accepted keys and concrete types.
-3. Move stable helpers shared by multiple features into an appropriately scoped
-   utility module. Do not let feature modules accumulate large collections of
-   unrelated private utility functions; keep a private helper local only when
-   it is single-purpose and tightly coupled to that feature.
-4. Keep every method on a key class within that class's stated responsibility,
-   and document non-obvious design decisions and invariants. Before adding a
-   method, prefer reuse, consolidation, or extension of an existing abstraction;
-   split the class when new behavior creates a separate responsibility or makes
-   the class unnecessarily long.
-5. Require changes to user-facing behavior to update `docs/`. When an existing
-   active module or feature design page owns the changed contract, update that
-   page. Require a new design page only when the reviewed branch's repository
-   policy, an accepted RFC/issue, or explicit maintainer acceptance criteria do
-   so; otherwise suggest it as non-blocking. For a major architectural change,
-   apply the branch's contributing policy for a design RFC or issue; the current
-   policy uses more than 500 changed production-code lines, excluding kernel,
-   data, config, and test changes. Resolve page status and authority through
-   [design-contracts.md](design-contracts.md), and do not demand a duplicate page
-   when an existing design owns the exact contract. When required, cover scope,
-   data flow, public contracts, failure behavior, alternatives, validation,
-   limitations, and rollout.
-6. Require every performance PR to provide reproducible base-versus-head A/B
-   results under the same hardware, software, model, workload, precision,
-   topology, warmup, repetitions, and measurement scope. Include exact commands,
-   variability, and a correctness or quality guard; one-sided or non-comparable
-   numbers are incomplete evidence. For a new model absent from the frozen base,
-   compare head with its pinned canonical reference implementation under rule 12
-   instead. Follow
-   [perf-verification.md](../checks/perf-verification.md) for the full protocol.
-7. Require every addition, removal, default change, or semantic change to a
-   user-facing inference API or CLI to explain why it is necessary, which
-   alternatives were considered, and why the chosen interface is preferable.
-   Record compatibility, deprecation or migration behavior, and the rationale
-   in the PR. Update the corresponding module and feature design documents when
-   they define the changed interface or workflow, or when policy requires one.
-8. Require every bug-fix PR to add an automated regression test that reproduces
-   the defect on the frozen base and passes on the fixed head. Exercise the
-   production path or nearest stable boundary and assert the corrected behavior,
-   not only process survival. Record the exact base/head command and result, and
-   place hardware- or model-specific coverage in the correct CI lane. A manual
-   reproduction supplements but does not replace the regression test.
-9. Require every new or materially changed recipe to follow
-   [`recipes/TEMPLATE.md`](../../../../../recipes/TEMPLATE.md) and the naming and
-   layout conventions in
-   [`recipes/README.md`](../../../../../recipes/README.md).
-   Complete every applicable summary, use-case, reference, hardware,
-   environment, exact-command, verification, and notes section with tested,
-   reproducible details; explain any intentional deviation in the PR.
-10. Require every new model to verify its supported modalities, platforms,
-    execution modes, and features with production-path evidence. Update
-    `docs/models/supported_models.md` and every applicable feature support or
-    compatibility table; do not claim support that the PR does not validate.
-    Follow
-    [model-addition-checklist.md](../checks/model-addition-checklist.md) for the
-    model-specific documentation checks.
-11. Require every new model PR to add or update its in-repository model-family
-    recipe under `recipes/` and its `recipes/README.md` index entry. Apply rule
-    9, and keep the recipe's model identifiers, tasks, serving modes, hardware,
-    commands, supported features, and limitations aligned with validated PR
-    evidence. An external recipe link does not replace the in-repository recipe.
-12. Require every new model to compare accuracy or output quality and performance
-    against a pinned baseline or canonical reference implementation. Match the
-    checkpoint, inputs, precision, hardware, workload, and measurement method;
-    provide exact commands, results, and explanations for material differences.
-    Prefer a detailed timing split for each stage and explain when it is
-    unavailable. Follow
-    [model-addition-checklist.md](../checks/model-addition-checklist.md) and
-    [perf-verification.md](../checks/perf-verification.md) for the evidence
-    contract.
-
-## Blocking risk scan
-
-| Risk | Prove before reporting |
-| --- | --- |
-| Correctness | A live input reaches a wrong output, exception, silent drop, shape/dtype/device mismatch, or partially initialized state. |
-| Compatibility | A supported API, config key, default, serialization schema, model identifier, or caller breaks without validation, migration, or deprecation. |
-| Lifecycle | Allocation or startup lacks cleanup on partial failure, timeout, cancellation, shutdown, or repeated requests. |
-| Concurrency/distribution | Ordering, identity, rank, world size, completion, timeout, backpressure, or collective assumptions fail on a supported path. |
-| Cache/shared state | Identity omits a correctness-affecting input, or isolation, invalidation, disabled behavior, eviction, or cleanup is incomplete. |
-| Async behavior | Blocking I/O, sleep, a lock across `await`, or unnecessary serialization harms a reachable async path. |
-| Security/data handling | Secrets, user payloads, unsafe deserialization/eval/shell, unvalidated paths, or unbounded metric labels are reachable. |
-| Validation evidence | Tests bypass the production dispatcher, mock away the change, use unrealistic types/MRO, or cannot fail when the defect returns. |
-| User contract | User-visible model, feature, API, CLI, config, default, or compatibility behavior changes without accurate docs or examples. |
-
-Search bounded callers and sibling implementations before reporting dead code,
-duplication, or a missed consumer. Keep new abstractions only when they have a
-distinct live caller, invariant, or compatibility need.
-
-## Finding bar
-
-Anchor each finding to a changed `path:line`; name the trigger or call path,
-current behavior, impact, and smallest fix direction. Treat pending CI, missing
-hardware, or unsupported measurements as validation gaps unless the repository
-contract makes that evidence a merge requirement.
@@ -1,191 +0,0 @@
-# Review Execution and Delivery
-
-Use this reference for every review. It defines snapshot collection, gates,
-validation records, delivery permissions, maintainer tone, and re-review.
-
-Official docs: [contributing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/)
-and [CI failure triage](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/failures/).
-
-## Contents
-
- [Freeze the review surface](#freeze-the-review-surface)
- [Report status before analysis](#report-status-before-analysis)
- [Apply review gates](#apply-review-gates)
- [Run bounded validation](#run-bounded-validation)
- [Deliver maintainer-style findings](#deliver-maintainer-style-findings)
- [Re-review safely](#re-review-safely)
-
-## Freeze the review surface
-
-For a GitHub PR, read the base/head SHA before and after fetching metadata and
-the diff:
-
-```bash
-gh api "repos/vllm-project/vllm-omni/pulls/<PR>" \
-  --jq '{base_sha: .base.sha, head_sha: .head.sha}'
-REVIEW_FIELDS="number,url,title,body,isDraft,baseRefName,headRefName,mergeable,mergeStateStatus,statusCheckRollup,files"
-gh pr view <PR> --repo vllm-project/vllm-omni \
-  --json "${REVIEW_FIELDS}"
-gh pr diff <PR> --repo vllm-project/vllm-omni
-gh api "repos/vllm-project/vllm-omni/pulls/<PR>" \
-  --jq '{base_sha: .base.sha, head_sha: .head.sha}'
-```
-
-Discard the snapshot if either SHA changed. Do not mix comments or validation
-from different heads.
-
-After the SHAs stabilize, fetch and materialize a trusted `head_sha` in an
-isolated detached worktree. Run every source read, `rg` search, import, and test
-from that snapshot, not the caller's checkout. A detached worktree provides
-snapshot isolation, not a security boundary.
-
-Treat a fork head as untrusted unless the user and environment policy explicitly
-establish trust. Never run its imports, tests, builds, hooks, package setup, or
-repo-configurable linters/plugins on the reviewer host. Execute them only in a
-disposable sandbox or VM with no credentials or inherited secrets, no host agent
-or service sockets, minimal read-only host mounts, disabled or explicitly
-allowlisted network, resource/time limits, and destruction after the run. If
-that boundary is unavailable, limit the review to the remote diff, SHA-addressed
-reads such as `git show <head_sha>:<path>`, and existing CI evidence; report all
-executable validation as a gap.
-
-Before the first source read, record a pristine snapshot fingerprint outside
-the reviewed worktree. Include `HEAD`, the NUL-delimited index entries and blob
-IDs, and a NUL-safe manifest of every worktree entry except Git metadata,
-including tracked, untracked, and ignored paths with file type, mode, symlink
-target, and content hash. Before each validation group and delivery, recompute
-and byte-compare the fingerprint as well as asserting `HEAD == head_sha`. If a
-tool changes or creates any entry, discard affected evidence and recreate the
-snapshot before another group; do not rely on `HEAD` alone or clean an unknown
-worktree in place. If an exact snapshot cannot be created, use SHA-addressed
-reads and report filesystem-dependent validation as a gap.
-
-For a local branch/worktree, determine the target ref from the user, current PR,
-or configured upstream; never infer it from the branch name. Resolve the target
-once and include all task-owned worktree state:
-
-```bash
-git status --porcelain=v2 -z
-git rev-parse HEAD
-git rev-parse <target-ref>
-git merge-base <target-base-sha> HEAD
-git diff --stat <comparison-commit>
-git diff --name-status <comparison-commit>
-git diff --binary <comparison-commit>
-git diff --cached --binary <comparison-commit>
-git diff --binary
-git ls-files --others --exclude-standard -z
-```
-
-Freeze the exact bytes of every in-scope untracked file from the NUL-delimited
-list, plus a NUL-safe path, file-type, mode, and content-hash manifest. Also
-fingerprint `HEAD`, the target and merge base, porcelain status, and both binary
-index and worktree patches. Recording only untracked names is insufficient.
-Keep these snapshots in the evidence packet and do not mutate the reviewed
-checkout during a read-only review.
-
-For local changes without PR metadata, mark the title/body as synthetic. Base
-them on the user request and commit messages without inventing validation claims.
-
-If no PR, branch, or usable worktree is identifiable, ask for a PR URL/number or
-explicit base and head rather than guessing.
-
-## Report status before analysis
-
-Within 60 seconds of starting, and before source searches or tests, send this
-host update:
-
-```text
-Pinned head: <SHA>
-Base/comparison: <ref and SHA>
-CI: <pass/fail/pending/not applicable>
-Mergeability: <state/not applicable>
-Preliminary findings: <brief finding or none yet>
-```
-
-Mark early findings as preliminary and continue. This is not a GitHub comment.
-
-## Apply review gates
-
- Report draft/WIP state. Continue a local review when explicitly requested,
-  but do not publish review events without separate authorization.
- Record DCO, pre-commit, required CI, and mergeability. Pending or unknown gates
-  do not block source review.
- Treat a failed gate as its own evidence. Do not restate its formatting/lint
-  output as a new code-review finding.
- Open CI logs only when the first failing step overlaps the frozen diff or
-  blocks the verdict. Start with the first error, not the last cascade.
- Treat the PR body as navigation. Commands, benchmark tables, and claimed tests
-  become evidence only after their provenance and relevance are checked.
-
-## Run bounded validation
-
-Keep one evidence packet for files read, bounded searches, callers, tests, CI,
-hardware, routes, and findings. Reuse it rather than refetching facts.
-
-Before pytest, run a short import/version compatibility check. Record each
-validation result with:
-
-```text
-repo, head SHA, command, result, Python/platform, dependency or lock fingerprint
-```
-
-After preflight, run targeted tests and low-cost static checks alongside source
-inspection when possible. Imports, tests, builds, and linters may create caches
-or rewrite files, so isolate each potentially mutating group in a disposable
-snapshot or recreate the pinned snapshot before continuing. Map source symbols
-to tests with bounded `rg` searches rather than assuming the test directory
-mirrors production paths.
-
-Classify failures as code, test, infrastructure, or flaky before reporting.
-Skipped hardware tests are gaps, not passes. For available hardware, verify the
-smallest representative unit/E2E path and compare actual output with PR claims.
-
-## Deliver maintainer-style findings
-
-Default to roughly 1-5 short comments, but treat that as calibration rather than
-a quota: report every real blocker and report no finding when there is no issue.
-
-Write each finding as:
-
-```text
-[P1] Short imperative title — path/to/file.py:<line>
-<Trigger or call path>. <Current behavior and impact>. <Smallest fix direction>.
-```
-
-Use [maintainer-style-study.md](../delivery/maintainer-style-study.md) for
-comment tone.
-Keep rule IDs, grades, and audit matrices internal unless the user asks for the
-complete audit.
-
-Verify every inline `path:line` against the frozen diff before delivery. For a
-PR, re-read the remote head and byte-compare the detached snapshot fingerprint,
-or recreate it from `head_sha`, before asserting current lines. For a local
-review, recompute and byte-compare the frozen `HEAD`, target, merge base, status,
-index patch, worktree patch, and untracked-content manifest. Any mismatch makes
-the review stale; discard the affected evidence and restart. Prefer one
-root-cause comment to several symptom comments.
-
-Local presentation is the default. Only explicit authorization permits GitHub
-posting. When authorized, publish one consolidated final review after
-validation; do not post preliminary or incremental comments. Submit a review
-event (`APPROVE`, `COMMENT`, or `REQUEST_CHANGES`) only when the user explicitly
-chooses that event.
-
-Reviewer requests and owner `@mention` comments are separate external writes;
-follow [review-requests.md](../delivery/review-requests.md) when the user asks
-for them.
-
-## Re-review safely
-
-Freeze the new head and compare it with the previously reviewed SHA. Then:
-
-1. inspect the delta and every file affected by conflict resolution or rebase;
-2. revalidate earlier findings against current lines and behavior;
-3. read unresolved, non-outdated threads and the author's evidence;
-4. rerun only checks invalidated by the delta;
-5. look for new regressions introduced by the fix;
-6. do not repeat resolved or outdated comments.
-
-If the target head changes during re-review, discard stale validation and start
-again from the new snapshot.
@@ -1,76 +0,0 @@
-# Module and Feature Review Routing
-
-Read [design-contracts.md](design-contracts.md) first. Route from the frozen
-head's live producer-consumer behavior, then confirm the result against its
-`docs/design/` metadata. Titles and paths are evidence, not the deciding rule.
-
-## Primary module contract
-
-Choose one primary module and a second only when the live call path crosses a
-documented dependency or primary-path exception.
-
-| Module | Live behavior signals | Read |
-| --- | --- | --- |
-| Entrypoints | Offline/CLI/API ingress, validation, rendering, streaming, sessions | [entrypoints.md](../modules/entrypoints.md) |
-| Configuration | Schema, defaults, deploy/stage construction, registry, topology | [configuration.md](../modules/configuration.md) |
-| I/O and Modality | Requests, messages, serialization, output types, accumulation, completion | [input-output-modality.md](../modules/input-output-modality.md) |
-| Error Contracts | Classification, fatality, propagation, sanitization, public rendering | [error-contracts.md](../modules/error-contracts.md) |
-| Engine Orchestration | Cross-stage routing, request state, ordering, RPC correlation, terminal convergence | [engine-orchestration.md](../modules/engine-orchestration.md) |
-| Stage Runtime | Placement, startup, readiness, replicas, affinity, membership, shutdown | [stage-runtime.md](../modules/stage-runtime.md) |
-| OmniConnector | Cross-stage/process/device/node transport and synchronization | [omni-connector.md](../modules/omni-connector.md) |
-| Model Integration | Registration, preprocessing, loading, runners, model-specific execution | [model-integration.md](../modules/model-integration.md) |
-| AR Runtime | Scheduling, request/cache state, adapters, workers, upstream vLLM semantics | [ar-runtime.md](../modules/ar-runtime.md) |
-| Diffusion Family | Diffusion runtime, models, batching, parallelism, or offload | [diffusion.md](../modules/diffusion.md) |
-| Execution Platforms | Hardware selection, capabilities, vendor workers, kernels, patches | [execution-platforms.md](../modules/execution-platforms.md) |
-| Cache Management | Cache identity, validity, reuse, eviction, reset, teardown | [cache-management.md](../modules/cache-management.md) |
-| Quantization | Method/metadata selection, layer mapping, reduced precision, constraints | [quantization.md](../modules/quantization.md) |
-| Observability | Metrics, logs, labels, units, correlation, lifecycle | [observability.md](../modules/observability.md) |
-| Profiling | Opt-in instrumentation, traces, start/stop lifecycle, overhead | [profiling.md](../modules/profiling.md) |
-| Benchmarking | Workloads, metric computation, benchmark CLI, result metadata | [benchmarking.md](../modules/benchmarking.md) |
-
-For tests-, docs-, CI-, or recipe-only changes, route to the production module
-whose contract they protect. When none exists, use the applicable evidence
-check without inventing a production owner.
-
-## Feature-design overlays
-
-Load every category whose documented behavior, enablement, default, support, or
-compatibility changes.
-
-| Feature-design section | Read |
-| --- | --- |
-| Runtime and stage execution | [runtime-stage-execution.md](../features/runtime-stage-execution.md) |
-| Communication and concrete connectors | [communication.md](../features/communication.md) |
-| Diffusion acceleration | [diffusion-acceleration.md](../features/diffusion-acceleration.md) |
-| Infrastructure and performance | [infrastructure-performance.md](../features/infrastructure-performance.md) |
-
-## Evidence and change overlays
-
-| Signal | Read | Optional repo-local skill |
-| --- | --- | --- |
-| New or expanded model, loader, processor, registry, or stage config | [model-addition-checklist.md](../checks/model-addition-checklist.md) | [`add-tts-model`](../../../add-tts-model/SKILL.md) or [`add-diffusion-model`](../../../add-diffusion-model/SKILL.md) |
-| Latency, throughput, memory, scaling, precision, or quality claim | [perf-verification.md](../checks/perf-verification.md) | [`diffusion-perf-opt`](../../../diffusion-perf-opt/SKILL.md) for diffusion |
-| Tests changed, absent for risky behavior, or test-only | [test-quality-evaluation.md](../checks/test-quality-evaluation.md) | [`vllm-omni-test`](../../../vllm-omni-test/SKILL.md) |
-| CI, examples, docs, public behavior, or contributor evidence | [tests-docs-checklist.md](../checks/tests-docs-checklist.md) | None |
-| Suitable hardware/server and runnable affected path | [verification.md](../checks/verification.md) | None |
-| User asks who should review or requests owner notification | [review-requests.md](../delivery/review-requests.md) | None |
-
-Use [`quantization`](../../../quantization/SKILL.md) for a quantization module
-change and [`$vllm-omni-npu-model-runner-upgrade`](../../../vllm-omni-npu-upgrade/SKILL.md)
-for an NPU execution-platform change when those skills are available.
-
-For a bug fix, require a reachable reproduction and regression test. For a
-refactor, prove parity and remove obsolete paths. For a feature, verify the
-public/config contract, module integration, compatibility/default behavior,
-production dispatch, feature design, and docs.
-
-## Calibrate findings
-
- **P0:** security exposure, data corruption, or broad project unusability.
- **P1:** reachable runtime failure, wrong output, compatibility break, or
-  unsafe lifecycle in the changed behavior.
- **P2:** real non-blocking defect with a concrete future failure mode.
-
-Treat draft candidate invariants, missing hardware, and unsupported claims as
-questions or validation gaps unless current code, tests, or policy makes them a
-merge requirement.
@@ -61,13 +61,6 @@ repos:
      types: [python]
      files: ^tests/

-    - id: check-tts-adapter-migration
-      name: Ratchet TTS per-model branches out of serving_speech.py
-      entry: python tools/pre_commit/check_tts_adapter.py
-      language: python
-      pass_filenames: false
-      files: ^vllm_omni/entrypoints/openai/(serving_speech\.py|tts_adapters/__init__\.py)$
-
    # Keep `suggestion` last
    - id: suggestion
      name: Suggestion
@@ -9,7 +9,7 @@ Easy, fast, and cheap omni-modality model serving for everyone
 </h3>

 <p align="center">
-| <a href="https://vllm-omni.readthedocs.io/en/latest/"><b>Documentation</b></a> | <a href="https://deepwiki.com/vllm-project/vllm-omni"><b>DeepWiki</b></a> | <a href="https://discuss.vllm.ai"><b>User Forum</b></a> | <a href="https://slack.vllm.ai"><b>Developer Slack</b></a> | <a href="docs/assets/WeChat.jpg"><b>WeChat</b></a> | <a href="https://arxiv.org/abs/2602.02204"><b>Paper</b></a> | <a href="https://docs.google.com/presentation/d/1aPj0OGl_-ZVoib-Qne5dGDAlrRFB-PdHl6E-EE99g8E/edit?usp=sharing"><b>Slides</b></a> |
+| <a href="https://vllm-omni.readthedocs.io/en/latest/"><b>Documentation</b></a> | <a href="https://deepwiki.com/vllm-project/vllm-omni"><b>DeepWiki</b></a> | <a href="https://discuss.vllm.ai"><b>User Forum</b></a> | <a href="https://slack.vllm.ai"><b>Developer Slack</b></a> | <a href="docs/assets/WeChat.jpg"><b>WeChat</b></a> | <a href="https://arxiv.org/abs/2602.02204"><b>Paper</b></a> | <a href="https://docs.google.com/presentation/d/111-L8zF7A1j_YI_cR8JsblofdScdRr2f/edit?usp=sharing&ouid=110473603432222024453&rtpof=true&sd=true"><b>Slides</b></a> |
 </p>


@@ -63,5 +63,5 @@ vLLM-Omni seamlessly supports most popular open-source models on HuggingFace, in

 For more information, checkout the following:

- [vllm-omni architecture design and recent roadmaps](https://docs.google.com/presentation/d/1aPj0OGl_-ZVoib-Qne5dGDAlrRFB-PdHl6E-EE99g8E/edit?usp=sharing)
+- [vllm-omni architecture design and recent roadmaps](https://docs.google.com/presentation/d/1XJWgv79lORl8rbaVvp2d5Sqs6ZEBgAgj/edit?slide=id.p1#slide=id.p1)
 - [vllm-omni announcement blogpost](https://blog.vllm.ai/2025/11/30/vllm-omni.html)
@@ -672,147 +672,100 @@ down and spawn a new one mid-module. A few rules that save real CI debugging tim

 ## Online Serving Integration

-To expose your model through the `/v1/audio/speech` OpenAI-compatible endpoint, write
-one adapter under `vllm_omni/entrypoints/openai/tts_adapters/`. The adapter declares
-how your model is recognized and owns its request handling; `serving_speech.py` should
-not need an edit.
+To expose your model through the `/v1/audio/speech` OpenAI-compatible endpoint, add
+**all five** of the following integration points to
+`vllm_omni/entrypoints/openai/serving_speech.py` in a **single commit**. Adding them
+piecemeal causes partial-integration failures that are hard to debug.

-### 1. Write the adapter
+### 1. Stage constant

-Create `vllm_omni/entrypoints/openai/tts_adapters/your_model.py`:
+Near the top of the file, alongside the other `_*_TTS_MODEL_STAGES` constants:

 ```python
-# SPDX-License-Identifier: Apache-2.0
-"""YourModel serving adapter."""
-
-from typing import TYPE_CHECKING
-
-from vllm_omni.entrypoints.openai.tts_adapters import register_tts_adapter
-from vllm_omni.entrypoints.openai.tts_adapters.base import ARTTSAdapter, PreparedRequest
-
-if TYPE_CHECKING:
-    from vllm_omni.entrypoints.openai.protocol.audio import OpenAICreateSpeechRequest
-
-
-@register_tts_adapter
-class YourModelAdapter(ARTTSAdapter):
-    # The registry key, and the model-type string used in logs.
-    name = "your_model"
-    # The engine ``model_stage`` value(s) your deployment yaml sets. Detection,
-    # stage discovery and `/v1/audio/speech` routing all derive from this.
-    stage_keys = frozenset({"your_model_stage_key"})
-
-    def validate(self, request: "OpenAICreateSpeechRequest") -> str | None:
-        """Return an error string, or None if the request is valid."""
-        if not request.input or not request.input.strip():
-            return "Input text cannot be empty"
-        return None
-
-    async def build(
-        self,
-        request: "OpenAICreateSpeechRequest",
-        sampling_params_list: list,
-        has_inline_ref_audio: bool,
-    ) -> PreparedRequest:
-        """Build the engine prompt and per-model parameters."""
-        params: dict[str, list] = {"text": [request.input]}
-        if request.voice is not None:
-            params["voice"] = [request.voice]
-        return PreparedRequest(
-            prompt={"prompt": request.input},
-            tts_params=params,
-            model_type=self.name,
-        )
+_YOUR_MODEL_TTS_MODEL_STAGES = {"your_model_stage_key"}
 ```

-Then add it to the import block at the bottom of
-`vllm_omni/entrypoints/openai/tts_adapters/__init__.py` so it registers on import.
-That import line is the only shared file a new model has to touch.
+### 2. Union into `_TTS_MODEL_STAGES`

-> **Pure-diffusion TTS does not go through adapters yet.** When the server is built
-> by `OmniOpenAIServingSpeech.for_diffusion()`, `create_speech()` routes straight to
-> `_create_diffusion_speech()` and never calls `validate()` or `build()`.
-> `DiffusionTTSAdapter` is scaffolding for that migration and has no production
-> subclass today, so validation or prompt construction placed in one would silently
-> never run. If your model is served by the diffusion engine rather than
-> `engine_client`, follow the existing diffusion path and say so on #4855 — wiring
-> that path through the adapter layer is open work, not something to do inside a
-> new-model PR.
-
-### 2. If a stage key alone cannot identify your model
-
-Two escape hatches, in order of preference:
+Add to the `_TTS_MODEL_STAGES` set union:

 ```python
-# The architecture is authoritative (e.g. your model has no dedicated
-# model_stage value, or shares one with another model).
-model_archs = frozenset({"YourModelForConditionalGeneration"})
-
-# Set this too if your model owns NO stage key, so stage discovery has to find
-# your AR entry stage by architecture.
-arch_identifies_entry_stage = True
+_TTS_MODEL_STAGES: set[str] = (
+    ...
+    | _YOUR_MODEL_TTS_MODEL_STAGES
+)
 ```

-If your rule is not a set-membership test, override `matches()` — see
-`covo_audio.py`, which shares the generic `fused_thinker_talker` stage key with
-non-CoVo deployments and confirms with the architecture:
+### 3. Model type detection
+
+In `_detect_tts_model_type()`, add before the final `return None`:

 ```python
-@classmethod
-def matches(cls, model_stage: str | None, model_arch: str | None) -> bool:
-    return super().matches(model_stage, model_arch) and bool(model_arch) and "CovoAudio" in model_arch
+if model_stage in _YOUR_MODEL_TTS_MODEL_STAGES:
+    return "your_model"
 ```

-If your model can match the same deployment as another adapter, give one of them an
-explicit `detect_priority` (lower runs first). `tests/entrypoints/openai_api/
-test_tts_detection.py` fails if two same-priority detectors can both match one input,
-so an unordered overlap cannot be merged.
+### 4. Request validation dispatch

-Models that are speech-capable only in some deployment topologies override
-`stage_serves_speech()` — see `audex.py`, whose omni thinker is text-final unless the
-speech decoder is deployed alongside it.
+In `_validate_tts_request()`, add before the fallback `return`:

-### 3. Reuse the shared helpers
+```python
+if self._tts_model_type == "your_model":
+    return self._validate_your_model_request(request)
+```

-Adapters reach shared serving helpers through `self.ctx.server`: reference-audio
-resolution (`_resolve_ref_audio`), uploaded-speaker handling
-(`_apply_uploaded_speaker`), format validation (`_validate_ref_audio_format`), and
-prompt-length limits (`_max_instructions_length`). Read a comparable adapter before
-writing your own — `fish_speech.py` for voice cloning, `higgs_audio_v3.py` for
-parameter-heavy models, `moss_tts.py` for a family sharing one base class.
+### 5. Validation and parameter-builder methods

-### 4. Test it
+Add two new methods:

-`tests/entrypoints/openai_api/test_tts_adapter.py` covers registry invariants and
-`test_tts_detection.py` covers detection. Add your model to
-`EXPECTED_MODEL_TYPES` in the former, and a case to the latter if you added a
-`model_archs` or `matches()` rule.
+```python
+def _validate_your_model_request(
+    self, request: OpenAICreateSpeechRequest
+) -> str | None:
+    """Validate YourModel request. Returns an error string or None."""
+    if not request.input or not request.input.strip():
+        return "Input text cannot be empty"
+    return None

-### Do not add branches to `serving_speech.py`
+def _build_your_model_params(
+    self, request: OpenAICreateSpeechRequest
+) -> dict[str, Any]:
+    """Build additional_information dict for YourModel."""
+    params: dict[str, Any] = {"text": [request.input]}
+    if request.voice is not None:
+        params["voice"] = [request.voice]
+    # Add any other model-specific fields here
+    return params
+```

-Older models predate the adapter framework and still have per-model branches in
-`serving_speech.py`; they are being migrated out (RFC #4327, #4855). Do not copy
-that pattern. `tools/pre_commit/check_tts_adapter.py` is a ratchet on the remaining
-`self._tts_model_type == ...` comparisons and fails the commit if the count grows.
+Then wire `_build_your_model_params` into the request-dispatch block in
+`_create_tts_request()` (search for the equivalent `_build_*_params` call for an
+existing model to find the right location). If the model supports voice cloning
+(`ref_audio` → `prompt_audio_path`, `ref_text` → `prompt_text`), add those mappings
+here too — follow any existing `_build_<model>_params` in `serving_speech.py` (e.g.
+`_build_moss_tts_params` for the voice-cloning variant) for the pattern.

-If your model genuinely needs behaviour that no adapter hook can express, that is a
-missing hook — propose it on the RFC rather than adding a branch.
+> **Two dispatch patterns coexist:** Fish Speech uses a `self._is_fish_speech` boolean
+> checked *before* `elif self._is_tts`. All newer models use the `_tts_model_type`
+> string pattern shown above. For new models, always use the string pattern — do not
+> add new `_is_*` boolean flags.
+
+> **Note on unused variables:** Only extract parameters in `_build_your_model_params`
+> that you actually pass to the model's generate / `inference_stream` call. Extracting
+> a variable without forwarding it will trigger a `ruff F841` pre-commit failure.

 ### Merge conflicts

-Your adapter is a new file, so it cannot conflict. The one shared line is your entry
-in the import block at the bottom of `tts_adapters/__init__.py`, which conflicts only
-when another model lands at the same time. The resolution is always to **keep both**
-imports — never discard either side. After resolving:
+`serving_speech.py` is modified by every new model PR and is the most common source of
+rebase conflicts. When rebasing onto `main` and a conflict appears here, the resolution
+is always to **keep both** the upstream model's additions and your own — never discard
+either side. After resolving:

 ```bash
-git add vllm_omni/entrypoints/openai/tts_adapters/__init__.py
+git add vllm_omni/entrypoints/openai/serving_speech.py
 git rebase --continue
 ```

-If you find yourself resolving a conflict inside `serving_speech.py`, something in
-your model is still going through the legacy path; see the note above.
-
 ## Single-Stage Models

 Some TTS models (e.g. MOSS-TTS-Nano) do not use a two-stage pipeline. Instead the
@@ -1,6 +1,6 @@
 # Architecture Overview

-This document outlines the architecture of vLLM-Omni.
+This document outlines the architectural design for vLLM-Omni.

 <p align="center">
  <picture>
@@ -9,456 +9,194 @@ This document outlines the architecture of vLLM-Omni.
  </picture>
 </p>

-## Design goals
+# Goals

-The primary goal of vLLM-Omni is to provide a fast and easy-to-use inference
-and serving engine for omni-modality models. vLLM-Omni extends vLLM's
-text-oriented autoregressive (AR) runtime with stage-based execution for
-non-textual outputs and non-autoregressive model components.
+The primary goal of the vLLM-Omni project is to build the fastest and easiest-to-use open-source Omni-Modality model inference & serving engine. vLLM-Omni extends the original vLLM, which was created to support large language models for text-based autoregressive (AR) generation tasks. vLLM-Omni is designed to support:

-The architecture is designed to:
+* **Non-textual Output:** Enables the integration, efficient processing and output of various data types, including but not limited to, images, audio, video, and action trajectories, alongside text.
+* **Non-Autoregressive Structure:** Support model structure beyond autoregressive, especially Diffusion Transformer (DiT), which is widely used in visual and audio generation.
+* **Integration with vLLM Core:** Maintain compatibility and leverage existing vLLM key modules and optimizations where applicable.
+* **Extensibility:** Design a modular and flexible architecture that can easily accommodate new modalities, model architectures, and output formats.

-* support text, image, audio, video, and action inputs and outputs;
-* compose autoregressive, generation, and diffusion stages in one pipeline;
-* reuse vLLM scheduling, cache, distributed-execution, and serving
-  primitives where they fit; and
-* keep model topology, deployment placement, runtime lifecycle, transport,
-  and public API concerns in separate layers.

-## Model execution
+# Representative omni-modality models

-These four examples show how vLLM-Omni maps model components to stage-local
-execution policies. Each summary covers the model-owned path, batching,
-attention, parallelism, quantization, and primary serving targets. The profiles
-are representative; a model may support multiple `PipelineConfig` and
-`DeployConfig` combinations.
+According to analysis for current popular open-source models, most of them have the combination of AR+DiT. Specifically, they can be further categorized into 3 types below:

-| Model | Model-owned path | vLLM-Omni stage view | Primary serving target |
-| --- | --- | --- | --- |
-| Qwen3-Omni | Thinker → Talker → Code2Wav | Three stages with asynchronous chunk hand-off | TTFT/TTFP, TPOT, E2EL, audio RTF, and concurrent throughput |
-| HunyuanImage-3.0 | Multimodal AR understanding/reasoning plus image-generation DiT | AR-only, DiT-only, or split AR → DiT deployment | DiT E2EL/denoising latency and image throughput; TTFT/TPOT for AR tasks |
-| MiniMax-H3 | Text encoder → task-specific FL2VA or Ref2VA DiT → video/audio VAE decoder | Three logical component/phase boundaries within one registered diffusion stage | Video/audio E2EL and media throughput; RTF when audio streaming is measured |
-| Cosmos3 | Unified MoT reasoner tower plus diffusion generator tower | One diffusion pipeline materializes both towers inside the stage | Image/video/action E2EL and throughput; RTF for synchronized audio |
-
-### Serving metric vocabulary
-
-The target metric follows the output modality, not just the model name.
-
-| Metric | Meaning in this document | Most useful for |
-| --- | --- | --- |
-| **TTFT** | Time to the first text token | AR reasoning or text output |
-| **TPOT** | Time per output token after the first token | AR decode stages |
-| **TTFP** | Time to the first streamed media packet, such as audio | Interactive speech and multimodal chat |
-| **E2EL** | End-to-end latency from request admission to the final output | Image, video, audio, and action requests |
-| **RTF** | Wall-clock processing time divided by generated audio duration; lower is faster than real time | Audio generation |
-| **Throughput** | Requests, tokens, or media seconds produced per wall-clock second | Offline and concurrent serving |
-
-### Qwen3-Omni: streaming AR pipeline
-
-Qwen3-Omni illustrates a multi-stage streaming AR pipeline: Thinker → Talker →
-Code2Wav. The [technical report](https://arxiv.org/abs/2509.17765) describes
-the model components, and the figure shows the stage-level streaming schedule
-used by vLLM-Omni.
+**DiT as a main structure, with AR as text encoder (e.g.: Qwen-Image)**
+  A powerful image generation foundation model capable of complex text rendering and precise image editing.

 <p align="center">
-  <a href="https://github.com/vllm-project/vllm-omni/blob/main/docs/source/architecture/qwen3-omni-async-chunk.png">
-    <img alt="Qwen3-Omni Thinker, Talker, and Code2Wav streaming stages" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/qwen3-omni-async-chunk.png" width="80%">
-  </a>
+  <picture>
+    <source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/dit-main-architecture.png">
+    <img alt="Qwen-Image" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/dit-main-architecture.png" width=30%>
+  </picture>
 </p>

-#### Model architecture by stage
-
-| Stage | Model component | Stage output |
-| --- | --- | --- |
-| **Thinker** | AuT audio encoder, SigLIP2 vision encoder, and the 30B-total/3B-active Thinker MoE Transformer | Text tokens and conditioning for the Talker |
-| **Talker** | 3B-total/0.3B-active Talker MoE Transformer with the MTP code-prediction path | Text tokens and audio codec tokens |
-| **Code2Wav** | Approximately 200M-parameter ConvNet audio decoder | Waveform/audio chunks |
-
-#### Representative stage execution
-
-| Stage | Batching | Attention and execution | Parallelism | Quantization |
-| --- | --- | --- | --- | --- |
-| **Thinker** | Continuous batching with stage-local `max_num_seqs` and token budgets | vLLM KV-cached AR attention; CUDA Graph execution when the stage is not eager | Independent stage placement; use the AR runtime's configured tensor parallelism | Supported ModelOpt FP8/NVFP4 or AutoRound checkpoint paths target the Thinker; encoders remain BF16 in the documented paths |
-| **Talker** | Continuous batching over autoregressive decode requests | KV-cached token decode with async-chunk output to Code2Wav | Independent stage placement; typically a separate GPU or replica from Thinker | BF16 baseline; no generic Talker quantization path is assumed |
-| **Code2Wav** | Static/chunk batching for codec-to-waveform decode | Non-AR chunked audio decode; eager execution is commonly retained | Separate stage or colocated placement, depending on the deployment | BF16 baseline; keep codec/vocoder precision model-specific |
-
-For this pipeline, the main serving target is interactive responsiveness:
-TTFT for text, TTFP for the first audio packet, TPOT for autoregressive decode,
-E2EL for the complete answer, and RTF/throughput for sustained audio serving.
-Async chunking and streaming primarily reduce TTFP and improve stage overlap;
-batching and CUDA Graphs primarily improve E2EL and throughput. See the
-[Qwen3-Omni recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen3-Omni.md)
-and [async chunk design](feature/async_chunk.md) for the deployment details.
-
-### HunyuanImage-3.0: shared multimodal model, split deployment choices
-
-HunyuanImage-3.0 illustrates a shared multimodal model with flexible AR, DiT,
-and split AR → DiT deployment. The official [technical
-report](https://arxiv.org/abs/2509.23951) provides the model view; the tables
-below map it to vLLM-Omni stages.
+**AR as a main structure, with DiT as multi-modal generator (e.g. BAGEL)**
+  A unified multimodal comprehension and generation model, with cot text output and visual generation.

 <p align="center">
-  <a href="https://github.com/Tencent-Hunyuan/HunyuanImage-3.0/blob/main/assets/framework.png">
-    <img alt="HunyuanImage-3.0 framework for understanding, language modeling, and image generation" src="https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanImage-3.0/main/assets/framework.png" width="95%">
-  </a>
+  <picture>
+    <source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/ar-main-architecture.png">
+    <img alt="Bagel" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/ar-main-architecture.png" width=30%>
+  </picture>
 </p>

-#### Model architecture by stage
-
-| Stage or component | Model component | Stage output |
-| --- | --- | --- |
-| **AR understanding/reasoning** | Understanding and generation encoders feeding the Hunyuan-A13B decoder-only Transformer and text detokenizer | Text responses or image-generation conditioning |
-| **Image generation** | Generation encoder, diffusion prediction path/Gen. Decoder, and the image VAE decode path | Image latents and final images |
-
-The vLLM-Omni deployment may expose the AR path only, the DiT path only, or
-both as an AR → DiT pipeline with a connector between them. That is a runtime
-decomposition of the model's capabilities; it should not be read as a claim
-that the published framework figure contains two unrelated backbones.
-
-#### Representative stage execution
-
-| Stage | Batching | Attention and execution | Parallelism | Quantization |
-| --- | --- | --- | --- | --- |
-| **AR** | Standard vLLM continuous batching when serving understanding/text tasks | KV-cached causal attention | Tensor/expert parallelism follows the selected AR deployment | Checkpoint-specific; do not infer DiT FP8 settings for the AR checkpoint |
-| **DiT + VAE** | Request batching or step-wise batching; Hunyuan step batching with more than one request requires `TORCH_SDPA` | `TORCH_SDPA` is used because the model mixes causal and full attention | Validated profiles include TP4, TP2 + sequence parallelism, TP2 + CFG parallelism, and expert parallelism for MoE weights | Online FP8 and ModelOpt mixed FP8/NVFP4 are documented for the DiT; VAE precision stays separate |
-
-Image generation is therefore measured mainly with per-image E2EL/denoising
-latency, peak memory, and images-per-second throughput. TTFT and TPOT remain
-meaningful for the optional AR understanding path, but they are not the right
-headline metrics for the DiT path. See the
-[HunyuanImage-3.0 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Tencent/HunyuanImage-3.0-Instruct.md)
-for the validated batching, attention, and quantization combinations.
-
-### MiniMax-H3: conditioning, denoising, and decode
-
-MiniMax-H3 illustrates logical component and phase boundaries between text
-encoding, task-specific denoising, and media decoding:
-`Text Encoder → DiT → VAE Decoder`. The current registered topology co-locates
-these components in one diffusion stage. These boundaries are useful for
-profiling and offload; independent placement would require a future
-multi-stage `PipelineConfig`. The stage mapping follows the implementation and
-serving recipe; the [release overview](https://minimaxi.com/blog/minimax-h3)
-notes that a detailed technical report is forthcoming.
-
-#### Model architecture by component
-
-| Logical component | Model component | Component output |
-| --- | --- | --- |
-| **Text Encoder** | Tokenizer/processor and Qwen3-VL text encoder; vision/audio references are prepared alongside the text condition | Packed multimodal conditioning for denoising |
-| **DiT** | Task-specific `FL2VA` DiT for text/first-frame generation or `Ref2VA` DiT for mixed references | Video and audio latent tokens |
-| **VAE Decoder** | Video VAE and audio VAE decode the generated latents and assemble the synchronized output | Decoded video frames and stereo waveform, with FPS and audio sample rate metadata |
-
-Both DiT partitions remain behind one task-selection point; `task` chooses
-which partition runs. In the current implementation, the three logical
-components execute inside one diffusion stage. This is different from
-Qwen3-Omni's three independently scheduled stages, even though both models
-produce synchronized audio and video-like outputs.
-
-#### Representative component execution
-
-| Logical component | Batching | Attention and execution | Parallelism | Quantization |
-| --- | --- | --- | --- | --- |
-| **Text Encoder** | The current co-located pipeline follows the diffusion request scheduler; independent prompt/reference batching would require a separate multi-stage topology | Qwen3-VL attention and multimodal preprocessing | `--text-encoder-tp-size N` shards the encoder across the first `N` DiT ranks; independent placement is not part of the current topology | BF16/FP32 baseline; the H3 DiT FP8 path does not quantize the text encoder |
-| **DiT** | The current H3 implementation executes one generation request per diffusion batch; use concurrency for service-level throughput | cuDNN attention for the validated two-GPU consumer profile; TRTLLM attention or FlashAttention-4 on supported Blackwell profiles | TP2 plus text-encoder TP and Ulysses/VAE parallel groups on multi-GPU profiles; DLO/CPU offload trade memory for transfer time | Online FP8 applies to eligible DiT linears and is incompatible with layerwise offload |
-| **VAE Decoder** | Decode follows each generation request; tile/patch work can be distributed even when denoising is not batched | VAE decode kernels rather than DiT attention | VAE patch parallelism and native tiled decode within the diffusion stage | BF16/FP32 baseline; the documented H3 FP8 path leaves both VAEs unchanged |
-
-The primary target is video/audio E2EL and media throughput, with the logical
-component boundaries making prompt encoding, denoising, and VAE decode costs
-separately measurable. RTF is useful when the audio stream is evaluated
-independently. TTFT and TPOT do not describe the main H3 generation path
-because the user-visible output is diffusion media rather than a token stream.
-The
-[MiniMax-H3 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3.md)
-contains the hardware-specific profiles and warmup requirements.
-
-### Cosmos3: unified MoT reasoner and generator
-
-Cosmos3 illustrates a unified Mixture-of-Transformers (MoT) reasoner and
-diffusion generator. The official [technical
-report](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf)
-and NVIDIA's [technical explanation](https://developer.nvidia.com/blog/develop-physical-ai-reasoning-world-and-action-models-with-nvidia-cosmos-3/)
-provide the two-tower model view used below.
+**AR+DiT (e.g. Qwen-Omni)**
+  A natively end-to-end omni-modal LLM for multimodal inputs (text/image/audio/video...) and outputs (text/audio...).

 <p align="center">
-  <a href="https://developer.nvidia.com/blog/develop-physical-ai-reasoning-world-and-action-models-with-nvidia-cosmos-3/">
-    <img alt="Cosmos3 autoregressive reasoner and diffusion generator towers" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/05/image-11-e1780000686151.webp" width="95%">
-  </a>
+  <picture>
+    <source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/ar-dit-main-architecture.png">
+    <img alt="Qwen-Omni" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/ar-dit-main-architecture.png" width=30%>
+  </picture>
 </p>

-#### Model architecture by stage
+# vLLM-Omni main architecture

-| Stage or component | Model component | Stage output |
-| --- | --- | --- |
-| **Reasoner tower** | Autoregressive VLM path with causal attention over language and optional vision/action context; runs once per generation request | Discrete reasoning/context tokens |
-| **Generator tower** | Diffusion path with full attention over the generator tokens and the reasoner K/V context; runs for each denoising step | Image, video, audio, or action tokens |
-| **Shared pipeline** | `Cosmos3OmniDiffusersPipeline` plus modality encoders/decoders and VAE paths | Final image/video/audio or action response |
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/vllm-omni-main-architecture.png">
+    <img alt="vLLM-Omni Main Architecture" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/vllm-omni-main-architecture.png" width=55%>
+  </picture>
+</p>

-The reasoner and generator are model-owned components, not two independent
-vLLM-Omni stages by default. The current Cosmos3 pipeline materializes both
-inside one diffusion stage; model-level CPU offload can swap the reasoner and
-generator components between their phases.
+## Key Components

-#### Representative stage execution
+| Component         | Description                                                                                                                              |
+| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
+| **OmniRouter**    | provide an intelligent router for Omni-modality requests dispatch                                                                        |
+| **EntryPoints**   | define the APIs for offline/online serving (APIServer, Omni/AsyncOmni), while `AsyncOmniEngine` and `Orchestrator` coordinate multi-stage AR/DiT execution |
+| **AR**            | adapted for omni-modality models while inheriting efficient features from vLLM, such as cache management                                 |
+| **Diffusion**     | natively implemented and optimized using acceleration components                                                                         |
+| **OmniConnector** | supports fully disaggregation based on E/P/D/G (Encoding/Processing/Decoding/Generation) disaggregation across stages                    |

-| Stage | Batching | Attention and execution | Parallelism | Quantization |
-| --- | --- | --- | --- | --- |
-| **Reasoner + generator pipeline** | Use request batching or step execution only when the selected pipeline advertises that capability; otherwise use `max_num_seqs=1` | Causal attention for reasoner tokens and full attention for diffusion tokens; the validated recipe uses a platform-selected aiter FlashAttention path with `TORCH_SDPA` fallback | Ulysses/context parallelism or tensor parallelism for the transformer; VAE tiling and layerwise/model-level offload address activation and weight memory | Online FP8 is supported for the diffusion pipeline; AutoRound/checkpoint-specific paths and quality validation remain separate from the BF16 baseline |
-
-For Cosmos3, generation E2EL and output throughput are the primary targets.
-Action-policy workloads add a control-loop latency target, while synchronized
-audio workloads add RTF. TTFT/TPOT are appropriate for a reasoner-only service,
-but not for the full diffusion generation path. See the
-[Cosmos3 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/cosmos3/Cosmos3-Nano.md)
-and [diffusion execution modes](../user_guide/diffusion/execution_modes.md)
-for the current runtime choices.
-
-## Why the stage-based architecture follows from these examples
-
-The four representative pipelines show that omni-modality serving is not one
-execution problem. Autoregressive decoding, diffusion denoising, multimodal
-encoding, and media decoding have different scheduling, attention, parallelism,
-memory, and quantization requirements. The architecture therefore needs a
-unit that can be optimized and resourced independently while remaining part of
-one request pipeline.
-
-| Observation | Design implication | vLLM-Omni response |
-| --- | --- | --- |
-| AR, diffusion, encoder, and decoder components have different execution loops | One scheduler and one execution policy cannot fit every component | Specialized AR, generation, and diffusion stage runtimes |
-| A model can be deployed as AR-only, DiT-only, or AR → DiT | Model structure must be separate from deployment topology | `PipelineConfig` describes logical stages and relationships; `DeployConfig` describes placement and resources |
-| Text encoders, DiTs, and VAE decoders have different batch and memory behavior | Batching, attention, parallelism, and quantization must be stage-local | Each stage carries its own runtime and engine configuration |
-| MiniMax-H3 can co-locate or logically split its text encoder and VAE decoder | A stage boundary should be configurable rather than forcing a process boundary | Logical stages can be co-located or assigned independent runtime placement |
-| Qwen3-Omni transfers hidden states and codec chunks across stages | Large intermediate data needs typed transport and synchronization | `OmniConnector` transports payloads and KV-cache data without owning model routing |
-| Requests span multiple stages and may be cancelled or produce ordered streaming output | Cross-stage request state needs a separate control plane | `Orchestrator` owns correlation, cancellation, routing state, and output ordering |
-| Qwen3-Omni optimizes first-packet latency while image/video models optimize E2EL and throughput | Performance objectives must be model- and stage-aware | TTFT/TPOT/TTFP, E2EL, RTF, and throughput are measured according to the output modality |
-
-This leads to a precise definition of a stage: it is a logical execution unit
-with its own model component, execution policy, resource ownership, and
-performance objectives. A stage is not necessarily a separate process. Cosmos3
-keeps its reasoner and generator inside one diffusion pipeline, while
-MiniMax-H3 exposes useful logical boundaries between text encoding, denoising,
-and VAE decoding. Both are valid mappings of the same abstraction.
-
-The resulting separation can be summarized as:
-
-```text
-Model structure       What is computed and how components are related
-        ↓
-PipelineConfig        Which logical stages exist and how they are connected
-        ↓
-Stage runtime policy  How each stage batches, attends, parallelizes, and quantizes
-        ↓
-DeployConfig           Where stages run, with which devices, replicas, and connectors
-```
-
-`AsyncOmniEngine` and `Orchestrator` coordinate the pipeline, `OmniConnector`
-transports stage outputs, and `StageRuntime` materializes the selected
-placement. This separation lets one logical model support multiple serving
-topologies without coupling model code to process layout or deployment
-resources.
-
-## System architecture
-
-The figure shows the main components of the stage-based runtime: entrypoints,
-the shared `AsyncOmniEngine`, request orchestration, stage lifecycle
-management, AR and diffusion execution modules, model/layer operations,
-connector transport, and multimodal outputs. `AsyncOmniEngine` is the
-composition root between the entrypoints and the orchestrator.
-
-```mermaid
-flowchart TB
-    subgraph omni["vLLM-Omni"]
-        subgraph entry["Entry points"]
-            api["API server"]
-            client["Omni / AsyncOmni"]
-        end
-        engine["AsyncOmniEngine<br/>composition root and background loop"]
-        orchestrator["Orchestrator<br/>request state and cross-stage routing"]
-        runtime["StageRuntime<br/>placement, replicas, readiness, and lifecycle"]
-        ar["AR module<br/>vLLM engine, scheduler, cache, executor, worker, and model runner"]
-        diffusion["Diffusion module<br/>scheduler, worker, model runner, and pipeline"]
-        ops["Model / layer / ops<br/>attention, parallelism, and quantization"]
-        connector["OmniConnector<br/>payload and KV transport plus synchronization"]
-        outputs["Multimodal outputs<br/>streaming chunks and final artifacts"]
-
-        api --> engine
-        client --> engine
-        engine --> orchestrator
-        engine --> runtime
-        orchestrator --> runtime
-        runtime --> ar
-        runtime --> diffusion
-        ar -. uses .-> ops
-        diffusion -. uses .-> ops
-        ar -. transports through .-> connector
-        diffusion -. transports through .-> connector
-        ar --> outputs
-        diffusion --> outputs
-    end
-```
-
-### Key components
-
-| Component | Responsibility |
-| --- | --- |
-| **Entrypoints** | Translate offline, CLI, OpenAI-compatible, and duplex requests into engine operations and render outputs back to public protocols. |
-| **Configuration resolution** | Combines pipeline topology, deployment settings, model metadata, and user overrides into a validated control-plane configuration. |
-| **AsyncOmniEngine** | Owns engine composition, the background event loop, stage initialization, request submission, and output collection. |
-| **Orchestrator** | Owns cross-stage request state, stage-to-stage routing, request correlation, cancellation, and output ordering. It does not own model selection or deployment placement. |
-| **StageRuntime** | Expands logical stages into local or distributed replicas, starts stage clients and processes, and manages readiness, affinity, failure, and shutdown. |
-| **AR runtime** | Extends vLLM's scheduler, KV-cache, worker, and model-runner path for omni-modality inputs and inter-stage outputs. |
-| **Diffusion runtime** | Schedules and executes denoising workloads through diffusion executors, workers, pipelines, acceleration backends, and output materialization. |
-| **OmniConnector** | Transports stage payloads and KV-cache data and provides synchronization. Connectors transport data; they do not choose the next logical stage. |
-| **Multimodal outputs** | `MultimodalPayload` separates tensor content from metadata, while `OmniRequestOutput` carries pipeline and diffusion results through the common output path. |
-
-## Configuration and runtime resolution
-
-The control plane has five conceptual layers. Authoring inputs are resolved
-once into a complete, transport-safe configuration before runtime processes are
-started. This keeps stage topology and model capabilities distinct from
-deployment placement and from process-local engine objects.
-
-The figure shows only the primary hand-off object for each layer; the detailed
-inputs, fields, and ownership rules are described below.
-
-```mermaid
-flowchart TB
-    layer1["Layer 1 · Authoring inputs<br/>PipelineConfig + DeployConfig"]
-    layer2["Layer 2 · Resolve once<br/>StageConfigFactory.create_from_model()<br/>VllmOmniConfig.from_pipeline_config()"]
-    layer3["Layer 3 · Transport-safe control plane<br/>VllmOmniConfig"]
-    layer4["Layer 4 · Runtime launch planning<br/>StageRuntime"]
-    layer5["Layer 5 · Engine materialization<br/>VllmConfig / OmniDiffusionConfig"]
-
-    layer1 --> layer2 --> layer3 --> layer4 --> layer5
-```
-
-The single resolution boundary is implemented by
-`StageConfigFactory.create_from_model()` and
-`VllmOmniConfig.from_pipeline_config()` in
-[`vllm_omni/config`](https://github.com/vllm-project/vllm-omni/tree/main/vllm_omni/config).
-The legacy `stage_args` YAML path remains only for models that have not yet
-migrated to `PipelineConfig` and `DeployConfig`.
-
-In the typed path, each stage configuration derives from
-`BaseVllmOmniStageConfig` and is specialized as
-`VllmOmniARStageConfig`, `VllmOmniGenerationStageConfig`, or
-`VllmOmniDiffusionStageConfig`. The request and engine-spec fields belong to the
-control-plane boundary; the current implementation stores their equivalent
-projections in the structured stage configuration and materializes
-backend-specific engine objects during stage initialization.
-
-The important ownership rules are:
-
-1. `PipelineConfig` is the source of truth for stage topology, execution type,
-   model capabilities, and stage relationships.
-2. `DeployConfig` describes placement, replicas, devices, connectors, and
-   deploy-time defaults; it does not redefine the model graph.
-3. CLI and Python overrides are applied at the resolution boundary, with
-   per-stage overrides taking precedence over global values where supported.
-4. `StageRuntime` owns launch planning and replica lifecycle. `ReplicaInitPlan`
-   is runtime-private state, not a user configuration object.
-5. `VllmConfig` and the enriched `OmniDiffusionConfig` are materialized in the
-   process that owns the corresponding engine.
+Disaggregated stages are managed through stage configuration. In Qwen3-Omni, Thinker/Talker/Code2wav are declared as separate configured stages, and runtime routing is handled by `Orchestrator` over `StageEngineCoreClient` / `StageDiffusionClient`.

 ## Main features

-The feature surface is grouped to match the
-[feature design documents](index.md#feature-design-documents). This page
-summarizes each feature's architectural role; the linked design document is
-the source for configuration, compatibility, and implementation details.
+vLLM-Omni aims to be fast, flexible, and easy to use with the following features:

-### Runtime and stage execution
+### Performance and Acceleration

-* **Disaggregated inference:** Logical stages can run in separate processes,
-  devices, or nodes while the orchestrator preserves their declared
-  relationships. `OmniConnector` implementations transfer stage data and
-  control-plane metadata. See [Disaggregated Inference](feature/disaggregated_inference.md).
-* **Asynchronous stage and output execution:** [Async Chunk](feature/async_chunk.md)
-  forwards partial stage outputs as they become available. [Async Diffusion
-  Output](feature/async_diffusion_output.md) overlaps device-to-host output
-  packing with the next diffusion request, while [Async Omni Output
-  Materialization](feature/omni_async_output_materialization.md) moves
-  CPU-side payload construction off the AR decode critical path.
-* **Automatic prefix caching:** [Automatic Prefix Caching in Omni Models](feature/prefix_caching.md)
-  reuses KV-cache-aligned stage outputs and multimodal tensors for requests
-  with common prefixes.
+The framework achieves high performance through several optimization techniques:

-### Communication
+* **Efficient AR Support:** Leverages efficient KV cache management inherited from vLLM.
+* **Pipelined Execution:** Uses pipelined stage execution overlapping to ensure high throughput.
+* **Full Disaggregation:** Relies on the OmniConnector and dynamic resource allocation across stages.
+* **Diffusion Acceleration:** Includes integrated support for diffusion acceleration. This is managed by the acceleration layer, which handles:
+    * **Cache:** Includes DBCache, TeaCache and third-party integration(e.g., [cache-dit](https://github.com/vipshop/cache-dit)).
+    * **Parallelism:** Supports TP, CP, USP, and CFG.
+    * **Attention:** Provides an interface for third-party integration (e.g., FA3, SAGE, MindIE-SD).
+    * **Quantization:** Supports various quantization implementations including FP8 and AWQ.
+    * **FusedOps:** Allows for custom and third-party integration.

-* **OmniConnector transport:** The connector contract carries tensors, KV-cache
-  data, and transport metadata across stage boundaries. The available
-  implementations cover shared memory and multi-node Mooncake, Mori, and
-  Yuanrong transports; see [Disaggregated Inference](feature/disaggregated_inference.md)
-  for the connector choices and configuration model.
+### Classifier-Free Guidance (CFG) Companion Flow

-### Diffusion acceleration
+vLLM-Omni natively models Classifier-Free Guidance (CFG) across disaggregated multi-stage setups via a "companion request" paradigm, eliminating redundant textual/multimodal context computation boundaries:
+1. **Prompt Expansion:** In the initial autoregressive (AR) stage, a customized `prompt_expand_func` hook intercepts incoming generation prompts and pairs them directly with negative companion prompts (e.g., a default negative prompt) on the fly, tagging the secondary prompt with a specific internal role (`cfg_text`).
+2. **Synchronized KV Cache Transfer:** The AR stage evaluates both the primary and companion sequence batches concurrently. The `OmniConnector` captures these specific structural dependencies and reliably passes the positive and negative outcome KV caches seamlessly across stage boundaries via shared memory or network protocols.
+3. **KV Cache Collection & Injection:** Upon reaching the downstream Diffusion (DiT) Engine, an assigned `cfg_kv_collect_func` automatically intercepts the mapped companion caches (`cfg_text_past_key_values`). These auxiliary dependencies are natively gathered and seamlessly bound to the primary generation sequence variables, enabling the DiT Engine to cleanly implement cross-attention CFG guidance over accurate conditioning and unconditioning structures in parallel.

-* **Request and step batching:** [Diffusion Continuous Batching](feature/diffusion_continuous_batching.md)
-  defines request-batch and step-batch execution, scheduler admission, and the
-  common streaming output path.
-* **Composable parallelism:** Diffusion stages can combine [CFG-Parallel](feature/cfg_parallel.md),
-  [Expert Parallel](feature/expert_parallel.md), [HSDP](feature/hsdp.md),
-  [Pipeline Parallel](feature/pipeline_parallel.md), [Sequence Parallel](feature/sequence_parallel.md),
-  [Tensor Parallel](feature/tensor_parallel.md), and [VAE Patch Parallelism](feature/vae_parallel.md)
-  according to the pipeline and hardware topology.
-* **Attention and cache acceleration:** [Skip-Softmax](feature/skip_softmax.md),
-  [Cache-DiT](feature/cache_dit.md), and [TeaCache](feature/teacache.md)
-  provide backend and denoising-step optimizations without changing the
-  stage contract.
-* **Quantization and memory efficiency:** [Quantization](feature/quantization.md)
-  resolves per-pipeline or per-component quantization configurations, while
-  [Distributed Layerwise Offload](feature/distributed_layerwise_offload.md)
-  streams diffusion blocks from host memory within the existing parallel
-  topology.
+### Flexibility and Usability

-## Interfaces
+vLLM-Omni is designed to be flexible and straightforward for users:

-The public interfaces map onto the same engine and stage boundaries:
+* **Heterogeneous Pipeline Abstraction:** Manages complex model workflows effectively.
+* **Hugging Face Integration:** Offers seamless integration with popular Hugging Face models.
+* **Distributed Inference:** Supports tensor, pipeline, data, and expert parallelism.
+* **Streaming Outputs:** Supports streaming outputs.
+* **Unified API:** Provides a consistent and unified API interface compatible with vLLM.
+* **OpenAI-compatible API Server:** Includes a FastAPI-based server for online serving that is compatible with the OpenAI API.
+
+# Interface design
+
+If you use vLLM, then you know how to use vLLM-Omni from Day 0:
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/vllm-omni-user-interface.png">
+    <img alt="vLLM-Omni interface design" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/architecture/vllm-omni-user-interface.png" width=55%>
+  </picture>
+</p>
+
+Taking **Qwen3-Omni** as an example:
+
+## Offline Inference
+The **Omni** class provides a Python interface for offline batched inference. Users initialize the Omni class with a Hugging Face model name and use the generate method, passing inputs that include both text prompts and multi-modal data:

-```mermaid
-flowchart LR
-    offline["Offline Python<br/>Omni.generate()"] --> engine["AsyncOmniEngine"]
-    online["OpenAI-compatible serving<br/>vllm serve ... --omni"] --> engine
-    duplex["Experimental duplex WebSocket<br/>/v1/duplex or realtime duplex"] --> engine
-    engine --> stages["Configured AR and diffusion stages"]
-    stages --> result["Streaming or final multimodal output"]
 ```
-
-### Offline inference
-
-The **Omni** class provides a Python interface for offline batched inference:
-
-```python
+# Create an omni runtime with HF model name.
 from vllm_omni.entrypoints.omni import Omni

 omni = Omni(model="Qwen/Qwen3-Omni-30B-A3B-Instruct")

-om_inputs = {
-    "prompt": prompt,
-    "multi_modal_data": {
-        "video": video_frames,
-        "audio": audio_signal,
-    },
-}
+# Example prompts.
+om_inputs = {"prompt": prompt,
+             "multi_modal_data": {
+                 "video": video_frames,
+                 "audio": audio_signal,
+             }}

+# Generate texts and audio from the multi-modality inputs.
 outputs = omni.generate(om_inputs, sampling_params_list)
 ```

-### Online serving
+## Online Serving
+Similar to vLLM, vLLM-Omni also provides a FastAPI-based server for online serving. Users can launch the server using the vllm serve command with the `--omni` flag:

-The OpenAI-compatible server uses the same stage configuration and engine
-boundaries:
-
-```bash
+```
 vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
 ```

-For example, a Qwen3-Omni chat request can contain text, image, audio, or
-video content and a `sampling_params_list` for its configured stages. See the
-[Qwen3-Omni serving example](../user_guide/examples/online_serving/qwen3_omni.md)
-and the [examples](https://github.com/vllm-project/vllm-omni/tree/main/examples)
-for complete requests.
+Users can send requests to the server using curl:

-Some pipelines expose additional OpenAI-compatible endpoints, such as joint
-video/audio generation. Endpoint support remains model-specific; consult the
-relevant model guide before assuming that every OpenAI route applies to every
-pipeline.
+```
+# prepare user content
+user_content='[
+        {
+          "type": "video_url",
+          "video_url": {
+            "url": "'"$SAMPLE_VIDEO_URL"'"
+          }
+        },
+        {
+          "type": "text",
+          "text": "Why is this video funny?"
+        }
+      ]'
+    sampling_params_list='[
+      '"$thinker_sampling_params"',
+      '"$talker_sampling_params"',
+      '"$code2wav_sampling_params"'
+    ]'
+    mm_processor_kwargs="{}"
+
+# send the request
+curl -sS -X POST http://localhost:8091/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d @- <<EOF
+{
+  "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+  "sampling_params_list": $sampling_params_list,
+  "mm_processor_kwargs": $mm_processor_kwargs,
+  "messages": [
+    {
+      "role": "system",
+      "content": [
+        {
+          "type": "text",
+          "text": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech."
+        }
+      ]
+    },
+    {
+      "role": "user",
+      "content": $user_content
+    }
+  ]
+}
+```
+
+For more usages, please refer to [examples](https://github.com/vllm-project/vllm-omni/tree/main/examples).
@@ -5,7 +5,6 @@ status: draft
 owners:
  - "@yuanheng-zhao"
  - "@Isotr0py"
-  - "@lishunyang12"
 primary_code_paths:
  - vllm_omni/diffusion/offloader/**
 related_code_paths:
@@ -20,12 +20,11 @@ extracts it into a shared, typed contract:
  (matching the bespoke caches it replaces), and reports per-device byte usage
  via `stats()` for observability.

-Autoregressive generation KV is *not* managed here: for DreamZero it is owned
-by the AR-Diffusion engine's paged KV pool (PR
-[#4534](https://github.com/vllm-project/vllm-omni/pull/4534)). Cosmos3's fixed,
-encode-once UND conditioning K/V is different and is covered by the dense
-Cosmos3 adapter described below. Integrating the engine's per-session paged KV
-handle into the same byte accounting is RFC #4480 Phase 1.
+Attention KV is *not* managed here: for DreamZero it is owned by the
+AR-Diffusion engine's paged KV pool (PR
+[#4534](https://github.com/vllm-project/vllm-omni/pull/4534)). The manager
+covers the model's non-KV session state; integrating the engine's per-session
+KV handle into the same byte accounting is RFC #4480 Phase 1.

 ## Enabling

@@ -159,62 +158,3 @@ of `num_frame_per_block` frames instead: identical output, bounded memory, and
 the per-step quantisation no longer scales with session length. Asking for more
 frames than the ring retains raises rather than silently returning a shorter
 window. The bespoke path is unchanged.
-
-### Cosmos3
-
-When `enable_session_state_manager` is enabled, the Cosmos3 adapter stores the
-dense, encode-once UND text K/V for every transformer layer and active CFG
-branch, together with that branch's GEN M-RoPE cosine/sine tensors. These are
-GPU-resident tensors and can contribute to CUDA OOM. A useful description of
-the retained storage on one rank is:
-
-```text
-sum_over_branches(
-  sum_over_layers(storage_bytes(K) + storage_bytes(V))
-  + storage_bytes(freqs_gen_cos) + storage_bytes(freqs_gen_sin)
-)
-```
-
-This is not a peak-memory upper bound: construction of the next branch can
-temporarily overlap the already retained branch with UND activations, the new
-full K/V result, RoPE tensors, and generator activations. K/V slices also keep
-their underlying allocation alive, so physical storage can follow the padded
-text length rather than only the exposed trimmed length. The manager's byte
-accounting deliberately measures storage for this reason.
-
-Branch placement changes the per-rank cost:
-
- no CFG retains one conditional branch;
- sequential CFG can retain both conditional and unconditional branches on the
-  same GPU;
- CFG-parallel retains one branch on each CFG rank;
- UND K/V is replicated across sequence-parallel ranks rather than divided by
-  the SP degree.
-
-Consequently, risk increases with text batch/sequence length, media token count
-(which sizes `freqs_gen`), sequential CFG, dtype width, and concurrent live
-requests. Phase 0 records `nbytes:cuda:*` but does not enforce `byte_budget`, so
-the manager cannot prevent an allocation from exhausting the device. The
-count-based session limit is not an OOM guarantee.
-
-The adapter transfers ownership by tensor reference; it does not clone K/V or
-RoPE tensors. For a normal serial request this should not materially increase
-tensor storage relative to Cosmos3's existing bespoke cond/uncond cache, which
-retains the same branch values. It does add small CPU-side session/object
-metadata. This claim is based on the reference flow in the implementation;
-there is not yet a current-head GPU peak-memory A/B result for this PR.
-
-Request-finally cleanup drops the manager-owned session, so branches do not
-accumulate with completed request IDs. The transformer handoff field still
-references the last loaded branch until `reset_cache()` runs at the start of
-the next generation (or the pipeline is destroyed). Thus this is bounded
-post-request residency, not growth per completed request, but manager
-`stats()` after `drop_session()` no longer includes that last transformer-held
-alias. A profiler that only reads manager statistics can therefore under-report
-live process memory.
-
-For OOM validation, measure complete cache-off and true flag-on generations in
-otherwise identical fresh processes. Synchronize CUDA and report process-level
-peak memory plus PyTorch peak allocated and peak reserved memory. Include the
-period between requests when checking cleanup; do not infer safety from the
-manager byte total, a single denoising step, or an operator-only profile.
@@ -123,7 +123,6 @@ def extract_omni_serve_subparser_init():
                        "TrackingNamespace": None,  # type annotation only
                        "make_arg_parser": lambda parser: parser,  # no-op for doc
                        "_ensure_vllm_platform": lambda: None,  # no-op for doc
-                        "_nonneg_finite_float": float,
                        "VLLM_SUBCMD_PARSER_EPILOG": "",
                        "logger": logger,
                        "DummySubparsers": DummySubparsers,
@@ -24,16 +24,6 @@ SERVING_MODE_TITLES = {
    "online_serving": "Online serving",
 }

-# Generated example pages keep their source-derived URLs even when their
-# navigation category changes. Quantization helpers are feature documentation,
-# not user-serving examples, so keep them under the existing Features /
-# Quantization section instead of creating a second top-level Quantization
-# category under Examples.
-EXAMPLE_NAV_TARGETS = {
-    "quantization": "quantization",
-}
-GENERATED_QUANTIZATION_EXAMPLES_TITLE = "Generated Examples"
-

 def load_model_display_names() -> dict[str, str]:
    try:
@@ -350,58 +340,26 @@ def update_nav_file(examples: list[Example]):
            examples_by_category[category] = []
        examples_by_category[category].append(example)

-    def category_items(category: str) -> list[dict[str, str]]:
-        items = []
-        for example in sorted(examples_by_category[category], key=lambda e: e.path.stem):
+    # Build the new Examples section - start with preserved items
+    examples_section = preserved_items.copy()
+
+    # Add examples grouped by category, sorted by category name
+    for category in sorted(examples_by_category.keys()):
+        category_examples = sorted(examples_by_category[category], key=lambda e: e.path.stem)
+        category_items = []
+        for example in category_examples:
            doc_path = EXAMPLE_DOC_DIR / example.category / f"{example.path.stem}.md"
            rel_path = doc_path.relative_to(ROOT_DIR / "docs")
-            items.append({example.nav_title: rel_path.as_posix()})
-        return items
+            category_items.append({example.nav_title: rel_path.as_posix()})

-    # Build the new Examples section - start with preserved items. Categories
-    # not explicitly routed elsewhere retain the historical Examples behavior.
-    examples_section = preserved_items.copy()
-    for category in sorted(examples_by_category.keys()):
-        if EXAMPLE_NAV_TARGETS.get(category, "examples") != "examples":
-            continue
-        items = category_items(category)
-        if items:
+        if category_items:
+            # Format category name (e.g., "offline_inference" -> "Offline Inference")
            category_title = fix_case(category.replace("_", " ").title())
-            examples_section.append({category_title: items})
+            examples_section.append({category_title: category_items})

    # Update the nav structure
    nav_list[user_guide_idx]["User Guide"][examples_idx]["Examples"] = examples_section

-    features_content = next(
-        (item["Features"] for item in user_guide_content if isinstance(item, dict) and "Features" in item),
-        None,
-    )
-    quantization_content = None
-    if isinstance(features_content, list):
-        quantization_content = next(
-            (item["Quantization"] for item in features_content if isinstance(item, dict) and "Quantization" in item),
-            None,
-        )
-
-    if isinstance(quantization_content, list):
-        # Remove only the group owned by this hook so repeated builds are
-        # idempotent and hand-authored Quantization navigation is retained.
-        quantization_content[:] = [
-            item
-            for item in quantization_content
-            if not (isinstance(item, dict) and GENERATED_QUANTIZATION_EXAMPLES_TITLE in item)
-        ]
-
-    quantization_examples = examples_by_category.get("quantization")
-    if quantization_examples:
-        if not isinstance(quantization_content, list):
-            logger.warning(
-                "Could not find 'User Guide' -> 'Features' -> 'Quantization' section; "
-                "omitting generated quantization examples from navigation"
-            )
-        else:
-            quantization_content.append({GENERATED_QUANTIZATION_EXAMPLES_TITLE: category_items("quantization")})
-
    # Write back to file
    nav_data["nav"] = nav_list
    with open(NAV_FILE, "w", encoding="utf-8") as f:
@@ -17,99 +17,83 @@ th {
 }
 </style>

-| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU | Recipe |
-|--------------|--------|-------------------|------------|---------|-----|-----------|--------|
-| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen3-Omni.md) |
-| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ |   |   |   | — |
-| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | | — |
-| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | | — |
-| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen-Image) |
-| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen-Image-2512.md) |
-| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | | — |
-| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | | — |
-| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ |   |   |   | — |
-| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | | — |
-| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | | — |
-| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2I, T2V, TI2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | | — |
-| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | ✅︎ | | | [Published](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3) |
-| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | | — |
-| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | | — |
-| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | | — |
-| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | | — |
-| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | | — |
-| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | | — |
-| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | | — |
-| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | | — |
-| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | | — |
-| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | | — |
-| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | | — |
-| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) |
-| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | | — |
-| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | | — |
-| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | | — |
-| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | | — |
-| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | | — |
-| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | | — |
-| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | | [Published](https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b) |
-| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | | — |
-| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | | — |
-| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | | — |
-| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | | — |
-| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | | — |
-| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | | — |
-| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | | — |
-| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | | — |
-| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | | — |
-| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | | — |
-| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | | — |
-|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | | — |
-| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | | — |
-| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | | — |
-
-The `Recipe` column links the corresponding deployment recipe. `Published` is
-preferred when a corresponding `recipes.vllm.ai` page exists; otherwise the
-link points to the repository recipe. `—` means that no recipe link has been
-added for that model row yet.
-
-For rows with an audited recipe link, the hardware checkmarks reflect hardware
-explicitly documented in that recipe. Other rows retain the implementation
-support metadata until their recipe is audited.
+| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU |
+|--------------|--------|-------------------|------------|---------|-----|-----------|
+| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ |   |   |   |
+| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ |
+| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | |
+| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | |
+| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | |
+| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | |
+| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ |   |   |   |
+| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | |
+| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | |
+| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | |
+| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | | | |
+| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | |
+| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | |
+| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ |
+| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | |
+| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ |
+| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ |
+| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | |
+| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | |
+| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | |
+| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | |
+| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | |
+| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ |
+| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ |
+| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ |
+| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ |
+| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | |
+| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | |
+| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | |
+| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | |
+| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | |
+| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | |
+| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | |
+| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | |
+| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | |
+| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | |
+| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ |
+| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | |
+| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | |
+| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | |
+| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ |
+| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | |
+| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | |
+| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | |
+| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | |
+| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | |
+| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | |
+| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | |
+|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | |
+| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | |
+| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | |

 ✅︎ indicates the model is supported on that backend. Empty cells mean not listed as supported on that backend.
-
-<sup>H3</sup> MiniMax H3 AMD GPU support is validated on gfx942 (MI300X) and
-gfx950 (MI350) in BF16, using the AITER `FLASH_ATTN` diffusion attention backend.
-Other AMD SKUs (e.g. MI325X) are not listed until their
-own validation evidence is added. See the
-[MiniMax H3 recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3) for
-per-architecture serving commands.
@@ -159,7 +159,7 @@ The following tables show which models support each feature:
 | **HunyuanVideo-1.5 T2V I2V** |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |  ✅ (encode/decode)   |       ✅        |        ❌         |
 | **DreamID-Omni**             |     ❌     |     ❌      |           ❌           |       ✅        |         ❌         |         ❌         |   ✅    |             ✅             |          ❌           |       ❌        |        ❌         |
 | **Cosmos3**                  |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |  ✅ (encode/decode)   |       ✅        |        ❌         |
-| **MiniMax-H3**               | ✅ (FL2VA) |     ✅      |           ✅           |       ❌        |       ✅ (DiT/TE)  |         ❌         |   ✅    |             ✅             |       ✅ (tile)       |      ✅ (DiT)      |        ❌         |
+| **MiniMax-H3**               |     ❌     |     ✅      |           ✅           |       ❌        |       ✅ (DiT/TE)  |         ❌         |   ✅    |             ✅             |       ✅ (tile)       |      ✅ (DiT)      |        ❌         |

 **Frame Interpolation Support**

@@ -33,25 +33,6 @@ This folder provides a unified CLI script for image-to-video generation using vL

 Default model: `Wan-AI/Wan2.2-I2V-A14B-Diffusers`.

-### LingBot-Video TI2V
-
-LingBot-Video accepts exactly one first-frame image and uses the same dense or
-MoE checkpoint as its T2I and T2V modes:
-
-```bash
-python examples/offline_inference/image_to_video/image_to_video.py \
-  --model robbyant/lingbot-video-dense-1.3b \
-  --model-class-name LingBotVideoPipeline \
-  --image /path/to/input.png \
-  --prompt "the fox looks toward the camera" \
-  --height 192 --width 320 --num-frames 9 --num-inference-steps 2 \
-  --guidance-scale 3.0 --flow-shift 3.0 --fps 24 \
-  --output lingbot_ti2v.mp4
-```
-
-The input image keeps its original geometry until the LingBot pipeline applies
-its model-specific resize and center crop.
-
 ## Prerequisites

 Download the example image used in the snippets below:
@@ -43,23 +43,6 @@ This folder provides several entrypoints for experimenting with text-to-image di

 Default model: `Qwen/Qwen-Image`

-### LingBot-Video
-
-LingBot-Video uses the same checkpoint for image and video generation. Run the
-shared T2I entry point with:
-
-```bash
-python examples/offline_inference/text_to_image/text_to_image.py \
-  --model robbyant/lingbot-video-dense-1.3b \
-  --prompt "a red fox standing in fresh snow" \
-  --height 192 --width 320 --num-inference-steps 2 \
-  --guidance-scale 3.0 --extra-body '{"flow_shift":3.0}' \
-  --output lingbot_t2i.png
-```
-
-The LingBot prompt builder selects the `image` output modality and requests one
-frame. Passing an input image is not supported in LingBot T2I mode.
-
 ## Quick Start

 ### Python API
@@ -55,21 +55,6 @@ python text_to_video.py \
  --output vace_t2v_output.mp4
 ```

-### LingBot-Video
-
-The dedicated LingBot example explicitly selects the video output modality:
-
-```bash
-python examples/offline_inference/text_to_video/text_to_video_lingbot.py \
-  --model robbyant/lingbot-video-dense-1.3b \
-  --height 192 --width 320 --num-frames 9 --num-inference-steps 2 \
-  --output lingbot_t2v.mp4
-```
-
-Use the same command with `robbyant/lingbot-video-moe-30b-a3b` for the MoE
-checkpoint. Requested frame counts are rounded upward to the causal
-VAE's `4n+1` grid.
-
 ### LTX-2

 ```bash
@@ -20,9 +20,9 @@ from vllm_omni.platforms import current_omni_platform

 def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="Generate text-to-video with a LingBot-Video checkpoint.")
-    parser.add_argument("--model", default="robbyant/lingbot-video-dense-1.3b")
+    parser.add_argument("--model", default="/home/models/lingbot-video-dense-1.3b")
    parser.add_argument("--prompt", default="a robotic arm picks up a red block")
-    parser.add_argument("--negative-prompt", default=None)
+    parser.add_argument("--negative-prompt", default="")
    parser.add_argument("--output", default="lingbot_video_output.mp4")
    parser.add_argument("--height", type=int, default=192)
    parser.add_argument("--width", type=int, default=320)
@@ -58,12 +58,9 @@ def _to_frame_array(video: Any) -> np.ndarray:
    if isinstance(video, torch.Tensor):
        tensor = video.detach().cpu()
        if tensor.dim() == 5:
-            tensor = tensor[0]
-        if tensor.dim() == 4 and tensor.shape[-1] not in (3, 4):
-            if tensor.shape[0] in (3, 4):
-                tensor = tensor.permute(1, 2, 3, 0)
-            elif tensor.shape[1] in (3, 4):
-                tensor = tensor.permute(0, 2, 3, 1)
+            tensor = tensor[0] if tensor.shape[1] not in (3, 4) else tensor[0].permute(1, 2, 3, 0)
+        elif tensor.dim() == 4 and tensor.shape[0] in (3, 4):
+            tensor = tensor.permute(1, 2, 3, 0)
        if tensor.is_floating_point():
            if float(tensor.min()) < 0.0:
                tensor = tensor.clamp(-1, 1) * 0.5 + 0.5
@@ -90,12 +87,8 @@ def main() -> None:
        parallel_config=DiffusionParallelConfig(),
    )

-    prompt: dict[str, Any] = {
-        "prompt": args.prompt,
-        "modalities": ["video"],
-        "num_frames": args.num_frames,
-    }
-    if args.negative_prompt is not None:
+    prompt: dict[str, str] = {"prompt": args.prompt}
+    if args.negative_prompt:
        prompt["negative_prompt"] = args.negative_prompt

    sampling_params = OmniDiffusionSamplingParams(
@@ -1,74 +0,0 @@
-# LingBot-Video
-
-LingBot-Video uses one `LingBotVideoPipeline` for text-to-image (T2I),
-text-to-video (T2V), and text-image-to-video (TI2V) generation. Both the dense
-and MoE checkpoints use the same request format.
-
-## Start the server
-
-```bash
-MODEL=robbyant/lingbot-video-dense-1.3b bash run_server.sh
-```
-
-The MoE checkpoint uses the same server and request scripts, but requires
-substantially more GPU memory:
-
-```bash
-MODEL=robbyant/lingbot-video-moe-30b-a3b bash run_server.sh
-```
-
-## Text to image
-
-The image endpoint selects T2I mode and always generates one frame:
-
-```bash
-bash run_curl_text_to_image.sh
-```
-
-The script sends a `320x192`, two-step smoke request and writes
-`lingbot_t2i.png`.
-
-## Text or text-image to video
-
-Run the video script without an image to select T2V mode:
-
-```bash
-bash run_curl_text_image_to_video.sh
-```
-
-Pass a first-frame image to the same script to select TI2V mode:
-
-```bash
-INPUT_IMAGE=/path/to/input.png bash run_curl_text_image_to_video.sh
-```
-
-The client scripts omit the optional `model` request field, so they target
-whichever dense or MoE checkpoint the server loaded. The video example uses the
-lightweight `320x192`, 9-frame, two-step configuration.
-
-Until the shared `/v1/videos` reference-image resizing is removed, TI2V target
-dimensions must be sent through `extra_params`, for example
-`{"size":"320x192"}`. Do not use the top-level `size`, `width`, or `height`
-fields for TI2V because the serving layer currently applies those dimensions
-to the reference image before the model receives it. T2V requests can continue
-to use the top-level dimension fields.
-
-LingBot video frame counts use the causal VAE `4n+1` grid. The pipeline rounds
-any requested frame count upward to the next valid value. An explicit
-`num_frames` takes precedence over `seconds`; otherwise, the server first
-resolves `seconds * fps` and the pipeline applies the same alignment.
-
-Official `resolution`/`ratio` presets can be sent through `extra_params`, for
-example `{"resolution":"720p","ratio":"16:9"}`. The `2k` and `4k` entries
-only define output dimensions; whether they run successfully depends on the
-checkpoint, GPU memory, and memory optimizations available in the deployment.
-
-For `/v1/images/generations`, the server resolves these aliases to their final
-pixel dimensions before applying `--max-generated-image-size`. Requests above
-the configured limit return HTTP 400 before engine dispatch. LingBot produces
-one output per prompt; image requests with `n>1` are also rejected with HTTP
-400.
-
-LingBot TI2V accepts exactly one image reference. Image editing, video
-references, audio references, batching, and Refiner execution are not supported
-by this pipeline mode.
@@ -1,67 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-if [ -n "${INPUT_IMAGE:-}" ] && [ ! -f "${INPUT_IMAGE}" ]; then
-    echo "INPUT_IMAGE does not exist: ${INPUT_IMAGE}"
-    exit 1
-fi
-
-BASE_URL="${BASE_URL:-http://localhost:8099}"
-POLL_INTERVAL="${POLL_INTERVAL:-2}"
-
-if [ -n "${INPUT_IMAGE:-}" ]; then
-    default_output="lingbot_ti2v.mp4"
-else
-    default_output="lingbot_t2v.mp4"
-fi
-OUTPUT_PATH="${OUTPUT_PATH:-${default_output}}"
-
-curl_args=(
-    -sS -X POST "${BASE_URL}/v1/videos"
-    -H "Accept: application/json"
-    -F "prompt=the subject turns toward the camera with smooth natural motion"
-    -F "num_frames=9"
-    -F "fps=24"
-    -F "num_inference_steps=2"
-    -F "guidance_scale=3.0"
-    -F "flow_shift=3.0"
-    -F "seed=42"
-)
-if [ -n "${INPUT_IMAGE:-}" ]; then
-    curl_args+=(
-        -F "input_reference=@${INPUT_IMAGE}"
-        -F 'extra_params={"size":"320x192"}'
-    )
-else
-    curl_args+=(-F "width=320" -F "height=192")
-fi
-
-create_response="$(curl "${curl_args[@]}")"
-
-video_id="$(echo "${create_response}" | jq -er '.id')"
-echo "Created video job ${video_id}"
-
-while true; do
-    status_response="$(curl -sS "${BASE_URL}/v1/videos/${video_id}")"
-    status="$(echo "${status_response}" | jq -er '.status')"
-    case "${status}" in
-        queued|in_progress)
-            sleep "${POLL_INTERVAL}"
-            ;;
-        completed)
-            break
-            ;;
-        failed)
-            echo "${status_response}" | jq .
-            exit 1
-            ;;
-        *)
-            echo "Unexpected video job status: ${status}"
-            exit 1
-            ;;
-    esac
-done
-
-curl -sS -L "${BASE_URL}/v1/videos/${video_id}/content" -o "${OUTPUT_PATH}"
-echo "Saved video to ${OUTPUT_PATH}"
@@ -1,20 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-BASE_URL="${BASE_URL:-http://localhost:8099}"
-OUTPUT_PATH="${OUTPUT_PATH:-lingbot_t2i.png}"
-
-curl -sS -X POST "${BASE_URL}/v1/images/generations" \
-    -H "Content-Type: application/json" \
-    -d "{
-        \"prompt\": \"a red fox standing in fresh snow\",
-        \"size\": \"320x192\",
-        \"num_inference_steps\": 2,
-        \"guidance_scale\": 3.0,
-        \"flow_shift\": 3.0,
-        \"seed\": 42,
-        \"response_format\": \"b64_json\"
-    }" | jq -er '.data[0].b64_json' | base64 -d > "${OUTPUT_PATH}"
-
-echo "Saved image to ${OUTPUT_PATH}"
@@ -1,10 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-MODEL="${MODEL:-robbyant/lingbot-video-dense-1.3b}"
-PORT="${PORT:-8099}"
-
-vllm serve "${MODEL}" --omni \
-    --model-class-name LingBotVideoPipeline \
-    --port "${PORT}"
@@ -0,0 +1,247 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Verify a ModelOpt FP8 diffusers checkpoint exported by
+quantize_wan2_2_modelopt_fp8.py / quantize_hunyuanvideo_15_modelopt_fp8.py.
+
+Three checks:
+  A. transformer/config.json has a sane quantization_config block.
+  B. transformer/*.safetensors contains FP8 (float8_e4m3fn) quantized tensors.
+  C. transformer disk size is materially smaller than a BF16 baseline.
+
+Example:
+    python examples/quantization/check_modelopt_fp8_export.py \\
+        --output ./hv15-480p-modelopt-fp8
+
+    # Optional: compare disk size against a local or HF BF16 baseline.
+    python examples/quantization/check_modelopt_fp8_export.py \\
+        --output ./hv15-480p-modelopt-fp8 \\
+        --baseline hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from collections import Counter
+from pathlib import Path
+
+SUPPORTED_ALGOS = ("FP8",)
+
+
+def _check_config(transformer_dir: Path) -> tuple[int, str | None]:
+    """Returns (status, quant_algo). status: 0 pass, 1 fail, 2 warn."""
+    cfg_path = transformer_dir / "config.json"
+    if not cfg_path.exists():
+        print(f"[FAIL] {cfg_path} missing.")
+        return 1, None
+
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+
+    qc = cfg.get("quantization_config")
+    if not isinstance(qc, dict):
+        print(f"[FAIL] No `quantization_config` block in {cfg_path}.")
+        return 1, None
+
+    print(f"[A] quantization_config from {cfg_path}:")
+    print(json.dumps(qc, indent=2))
+
+    quant_algo = qc.get("quant_algo")
+    issues = []
+    if qc.get("quant_method") != "modelopt":
+        issues.append(f"quant_method={qc.get('quant_method')!r} (expected 'modelopt')")
+    if quant_algo not in SUPPORTED_ALGOS:
+        issues.append(
+            f"quant_algo={quant_algo!r} (expected one of {SUPPORTED_ALGOS} — vllm-omni adapter may not auto-detect)"
+        )
+
+    if issues:
+        print("[A] WARN — config looks incomplete:")
+        for issue in issues:
+            print(f"    - {issue}")
+        return 2, quant_algo
+    print(f"[A] PASS — config looks correct (quant_algo={quant_algo}).")
+    return 0, quant_algo
+
+
+def _read_safetensors_header(path: Path) -> dict:
+    """Read the JSON header of a safetensors file. Bypass-safe — doesn't materialize tensors.
+
+    Returns {tensor_name: {'dtype': 'F8_E4M3', 'shape': [...], 'data_offsets': [...]}}.
+    Header dtype strings: F8_E4M3, F8_E5M2, BF16, F16, F32, F64, I8, I16, I32, I64, BOOL, U8, ...
+    """
+    import struct
+
+    with open(path, "rb") as f:
+        header_len = struct.unpack("<Q", f.read(8))[0]
+        header = json.loads(f.read(header_len))
+    header.pop("__metadata__", None)
+    return header
+
+
+def _classify_weight_scale_granularity(weight_scale_shapes: list[list[int]]) -> str:
+    """Infer per-tensor vs per-channel vs per-block from sample weight_scale shapes.
+
+    ModelOpt block-wise produces shapes like `[16, 1, 16, 1]` (broadcasting dims of 1
+    interleaved with block-count dims). We count "meaningful" dims — ones with size > 1 —
+    and classify: 0 meaningful dims = per-tensor (scalar), 1 = per-channel, 2+ = per-block.
+    """
+    if not weight_scale_shapes:
+        return "no weight_scale tensors found"
+
+    def meaningful_dims(shape: list[int]) -> int:
+        return sum(1 for d in shape if d > 1)
+
+    per_tensor = sum(1 for s in weight_scale_shapes if meaningful_dims(s) == 0)
+    per_channel = sum(1 for s in weight_scale_shapes if meaningful_dims(s) == 1)
+    per_block = sum(1 for s in weight_scale_shapes if meaningful_dims(s) >= 2)
+    total = len(weight_scale_shapes)
+    if per_tensor == total:
+        return "per-tensor (all scalar scales)"
+    if per_channel == total:
+        return "per-channel (1 meaningful dim)"
+    if per_block == total:
+        return "per-block (2+ meaningful dims — e.g. [M//bm, 1, N//bn, 1] for tiles)"
+    return f"mixed: per-tensor={per_tensor}, per-channel={per_channel}, per-block={per_block} of {total}"
+
+
+def _check_safetensors(transformer_dir: Path) -> int:
+    """Returns 0 on pass, 1 on fail. Reads on-disk dtype from the safetensors header."""
+    files = sorted(transformer_dir.glob("*.safetensors"))
+    if not files:
+        print(f"[FAIL] No *.safetensors in {transformer_dir}.")
+        return 1
+
+    header_dtype_counts: Counter[str] = Counter()
+    sample_quant_weight_keys: list[str] = []
+    sample_scale_keys: list[str] = []
+    weight_scale_shapes: list[list[int]] = []
+    sample_weight_scale_entries: list[tuple[str, list[int]]] = []
+
+    for f in files:
+        try:
+            header = _read_safetensors_header(f)
+        except Exception as exc:
+            print(f"[B] WARN — could not parse header of {f}: {exc}")
+            continue
+        for k, info in header.items():
+            dtype = info.get("dtype", "?")
+            header_dtype_counts[dtype] += 1
+            # FP8 stores weights as F8_E4M3 directly.
+            if dtype.startswith("F8") and k.endswith(".weight") and len(sample_quant_weight_keys) < 5:
+                sample_quant_weight_keys.append(k)
+            if k.endswith(("_scale", ".weight_scale", ".input_scale", "_scale_inv")) and len(sample_scale_keys) < 5:
+                sample_scale_keys.append(k)
+            if k.endswith(".weight_scale"):
+                weight_scale_shapes.append(info.get("shape", []))
+                if len(sample_weight_scale_entries) < 5:
+                    sample_weight_scale_entries.append((k, info.get("shape", [])))
+
+    print(f"\n[B] On-disk dtype counts across {len(files)} safetensors file(s) (from header, not get_tensor):")
+    for dtype, count in sorted(header_dtype_counts.items(), key=lambda kv: -kv[1]):
+        marker = "  <-- FP8" if dtype.startswith("F8") else ""
+        print(f"    {dtype:10s} {count:>6d}{marker}")
+
+    quant_count = sum(c for d, c in header_dtype_counts.items() if d.startswith("F8"))
+    if quant_count == 0:
+        print("[B] FAIL — no FP8 tensors on disk. Calibration likely did not actually quantize the weights.")
+        return 1
+
+    print(f"[B] PASS — {quant_count} FP8 tensors stored on disk.")
+    if sample_quant_weight_keys:
+        print(f"    sample quantized weight tensors: {sample_quant_weight_keys[:3]}")
+    if sample_scale_keys:
+        print(f"    sample scale tensors:            {sample_scale_keys[:3]}")
+    print("    (Note: torch's get_tensor() may return these as bf16 views on some versions —")
+    print("     irrelevant; vLLM's loader uses native FP8 ops.)")
+
+    # Weight-scale granularity — per-tensor (scalar) vs per-channel (1-D) vs per-block (N-D).
+    print(f"\n    weight_scale granularity: {_classify_weight_scale_granularity(weight_scale_shapes)}")
+    for key, shape in sample_weight_scale_entries[:3]:
+        print(f"      {key}: shape {shape}")
+    return 0
+
+
+def _disk_size_gib(p: Path) -> float:
+    return sum(f.stat().st_size for f in p.rglob("*") if f.is_file()) / (1024**3)
+
+
+def _check_size_vs_baseline(transformer_dir: Path, baseline: str | None) -> int:
+    """Returns 0 always (informational only)."""
+    quant_size = _disk_size_gib(transformer_dir)
+    print(f"\n[C] FP8 transformer disk size: {quant_size:.2f} GiB")
+
+    if baseline is None:
+        print("[C] SKIP — pass --baseline <path or HF id> to compare against BF16.")
+        return 0
+
+    baseline_path = Path(baseline)
+    if not baseline_path.exists():
+        # Try HF download.
+        try:
+            from huggingface_hub import snapshot_download
+        except ImportError:
+            print("[C] SKIP — huggingface_hub not installed and baseline not a local path.")
+            return 0
+        print(f"    Downloading baseline transformer from HF: {baseline}")
+        baseline_path = Path(snapshot_download(baseline, allow_patterns=["transformer/*"]))
+
+    bf16_dir = baseline_path / "transformer" if (baseline_path / "transformer").exists() else baseline_path
+    bf16_size = _disk_size_gib(bf16_dir)
+    if bf16_size == 0:
+        print(f"[C] WARN — baseline transformer dir empty: {bf16_dir}")
+        return 0
+
+    # Expected reduction for FP8: ~50%.
+    min_reduction = 30
+    reduction = (1 - quant_size / bf16_size) * 100
+    print(f"[C] BF16 baseline transformer disk size: {bf16_size:.2f} GiB ({bf16_dir})")
+    print(f"[C] Disk reduction: {reduction:.1f}%  (FP8 transformer is {quant_size / bf16_size:.0%} of BF16)")
+    if reduction < min_reduction:
+        print(
+            f"[C] WARN — FP8 should typically reduce disk by ~40-50%; <{min_reduction}% suggests partial quantization."
+        )
+    return 0
+
+
+def main() -> None:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    p.add_argument("--output", required=True, help="Path to the exported ModelOpt FP8 checkpoint root.")
+    p.add_argument(
+        "--baseline",
+        default=None,
+        help="Optional BF16 baseline (local diffusers dir or HF id) for disk-size comparison.",
+    )
+    args = p.parse_args()
+
+    out_root = Path(args.output).expanduser().resolve()
+    transformer_dir = out_root / "transformer"
+    if not transformer_dir.exists():
+        print(f"[FAIL] {transformer_dir} does not exist.")
+        sys.exit(1)
+
+    print(f"Checking: {out_root}\n")
+
+    fail = 0
+    config_status, _quant_algo = _check_config(transformer_dir)
+    fail |= config_status
+    fail |= _check_safetensors(transformer_dir)
+    _check_size_vs_baseline(transformer_dir, args.baseline)
+
+    print()
+    if fail == 0:
+        print("=" * 60)
+        print("ALL CHECKS PASSED — checkpoint looks ready for vllm-omni serving.")
+    elif fail == 1:
+        print("=" * 60)
+        print("FAILURES detected — calibration may need to be re-run.")
+        sys.exit(1)
+    else:
+        print("=" * 60)
+        print("WARNINGS only — checkpoint may serve but with caveats. See [A] above.")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,448 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Quantize HunyuanVideo-1.5 (480p T2V) to a ModelOpt FP8 Hugging Face checkpoint.
+
+Calibrates the DiT transformer using a small video prompt set and exports a
+diffusers-style directory whose transformer carries ModelOpt FP8 metadata.
+The exported checkpoint is consumable by vllm-omni's ModelOpt FP8 adapter
+(see vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py).
+
+Layers kept full precision match the #2728 / #2795 pattern: modulation,
+AdaLayerNorm, entry/exit projections, embeddings, the token refiner path,
+and final proj_out. MHA quantizers are off by default; HV-1.5 self-attention
+empirically degrades under FP8 (see #2920 ablation).
+
+Example:
+    python examples/quantization/quantize_hunyuanvideo_15_modelopt_fp8.py \\
+        --model hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v \\
+        --output ./hv15-480p-modelopt-fp8 \\
+        --overwrite
+"""
+
+from __future__ import annotations
+
+import argparse
+import copy
+import json
+import re
+import shutil
+import sys
+from pathlib import Path
+from typing import Any
+
+import torch
+from diffusers import DiffusionPipeline
+
+DEFAULT_PROMPTS = [
+    "A dog running across a field of golden wheat.",
+    "An astronaut riding a horse across the surface of Mars, red dust swirling, cinematic wide shot.",
+    "A hummingbird hovering in front of a vibrant red flower, slow motion, macro shot.",
+    "A crackling campfire at night under a starry sky, sparks rising into the dark.",
+    "An underwater shot of a coral reef with tropical fish swimming by, sun rays piercing the water.",
+    "A close-up of a blooming rose covered in morning dew, soft natural light.",
+    "A peaceful mountain village at dawn, mist rolling over the rooftops, cinematic establishing shot.",
+    "A skateboarder doing a kickflip in an urban plaza, slow motion, golden hour lighting.",
+]
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    p.add_argument("--model", required=True, help="Input HV-1.5 diffusers directory or HF id.")
+    p.add_argument("--output", required=True, help="Output directory for the ModelOpt FP8 checkpoint.")
+    p.add_argument("--dtype", choices=("bfloat16", "float16"), default="bfloat16")
+    p.add_argument("--height", type=int, default=480)
+    p.add_argument("--width", type=int, default=832)
+    p.add_argument(
+        "--num-frames",
+        type=int,
+        default=33,
+        help="Frames per calibration sample. 33 matches the typical short benchmark.",
+    )
+    p.add_argument("--guidance-scale", type=float, default=6.0)
+    p.add_argument(
+        "--calib-steps",
+        type=int,
+        default=10,
+        help="Denoising steps per calibration prompt (10 is enough for amax statistics).",
+    )
+    p.add_argument("--calib-size", type=int, default=8, help="How many prompts to use for calibration.")
+    p.add_argument("--seed", type=int, default=42)
+    p.add_argument(
+        "--prompt",
+        action="append",
+        default=[],
+        help="Custom calibration prompt. Repeat to provide multiple.",
+    )
+    p.add_argument(
+        "--quantize-mha",
+        action="store_true",
+        help="Enable FP8 attention K/V/softmax quantizers. Off by default — empirically degrades HV-1.5 video output.",
+    )
+    p.add_argument(
+        "--weight-block-size",
+        type=str,
+        default=None,
+        help="Per-block weight quantization as 'M,N' (e.g. '128,128' for 128x128 tiles). "
+        "Default: per-tensor (one scale per linear). Block-wise typically gives tighter quality at "
+        "negligible memory cost. Static FP8 is exempt from upstream vLLM's online block-wise gate.",
+    )
+    p.add_argument("--overwrite", action="store_true", help="Replace an existing output directory.")
+    return p
+
+
+def _parse_block_size(spec: str | None) -> list[int] | None:
+    if spec is None:
+        return None
+    parts = [int(x) for x in spec.split(",") if x.strip()]
+    if len(parts) != 2:
+        raise SystemExit(f"--weight-block-size must be 'M,N' (2 ints), got {spec!r}")
+    return parts
+
+
+def _require_modelopt() -> Any:
+    try:
+        import modelopt.torch.quantization as mtq
+    except ModuleNotFoundError as exc:
+        raise SystemExit(
+            "NVIDIA ModelOpt is not installed. Install with:\n"
+            "  pip install 'nvidia-modelopt[all]'\n"
+            f"Original error: {exc}"
+        ) from exc
+    return mtq
+
+
+def _ensure_paths(args: argparse.Namespace) -> tuple[str, Path]:
+    model_path = args.model
+    output_dir = Path(args.output).expanduser().resolve()
+    if output_dir.exists():
+        if not args.overwrite:
+            raise SystemExit(f"Output directory already exists: {output_dir}\nPass --overwrite to replace it.")
+        shutil.rmtree(output_dir)
+    return model_path, output_dir
+
+
+def _select_dtype(name: str) -> torch.dtype:
+    return {"bfloat16": torch.bfloat16, "float16": torch.float16}[name]
+
+
+def _build_prompts(args: argparse.Namespace) -> list[str]:
+    prompts = args.prompt or DEFAULT_PROMPTS
+    if args.calib_size <= 0:
+        raise SystemExit("--calib-size must be positive.")
+    if len(prompts) < args.calib_size:
+        repeats = (args.calib_size + len(prompts) - 1) // len(prompts)
+        prompts = (prompts * repeats)[: args.calib_size]
+    return prompts[: args.calib_size]
+
+
+# Layers to KEEP at full precision (mirror of the #2920 wiring + #2728/#2795 skip pattern).
+# - x_embedder, image_embedder, context_embedder*, time_embed*, cond_type_embed: entry/embedding
+# - norm_out, norm1*.linear, norm1_context*.linear, norm2*, norm2_context*: AdaLayerNorm modulation
+# - proj_out: final output projection
+# - token_refiner*: text-encoder refinement uses diffusers raw nn.Linear
+def _filter_func_hv15(name: str) -> bool:
+    pattern = re.compile(
+        r"(proj_out.*|"
+        r".*(x_embedder|image_embedder|context_embedder|context_embedder_2|"
+        r"time_embed|cond_type_embed|"
+        r"norm_out|norm1\.linear|norm1_context\.linear|norm2|norm2_context|"
+        r"token_refiner).*)"
+    )
+    return pattern.match(name) is not None
+
+
+def _mha_filter_func(name: str) -> bool:
+    pattern = re.compile(
+        r".*(q_bmm_quantizer|k_bmm_quantizer|v_bmm_quantizer|softmax_quantizer|bmm2_output_quantizer).*"
+    )
+    return pattern.match(name) is not None
+
+
+def _disable_known_problematic_quantizers(mtq: Any, backbone: torch.nn.Module, *, quantize_mha: bool) -> None:
+    if not hasattr(mtq, "disable_quantizer"):
+        return
+    mtq.disable_quantizer(backbone, _filter_func_hv15)
+    if not quantize_mha:
+        mtq.disable_quantizer(backbone, _mha_filter_func)
+
+
+def _load_pipeline(model_path: str, dtype: torch.dtype) -> DiffusionPipeline:
+    pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=dtype)
+    if hasattr(pipe, "set_progress_bar_config"):
+        pipe.set_progress_bar_config(disable=True)
+    pipe.to("cuda")
+    return pipe
+
+
+def _build_forward_loop(pipe: DiffusionPipeline, args: argparse.Namespace, prompts: list[str]):
+    generator = torch.Generator(device="cuda")
+
+    # Try to set guidance on the pipeline's guider object up front (modern
+    # diffusers HV-1.5 uses a Guider abstraction, not a per-call kwarg). Falls
+    # back silently — calibration uses whatever default the pipeline ships with.
+    guider = getattr(pipe, "guider", None)
+    if guider is not None and hasattr(guider, "guidance_scale"):
+        try:
+            guider.guidance_scale = args.guidance_scale
+        except Exception:
+            pass
+
+    base_kwargs = dict(
+        height=args.height,
+        width=args.width,
+        num_frames=args.num_frames,
+        num_inference_steps=args.calib_steps,
+        output_type="latent",
+    )
+
+    def forward_loop(*_unused_args, **_unused_kwargs) -> None:
+        with torch.inference_mode():
+            for idx, prompt in enumerate(prompts):
+                generator.manual_seed(args.seed + idx)
+                # Try with guidance_scale first; fall back without on TypeError
+                # for pipelines (like HV-1.5) that take CFG via guider config.
+                try:
+                    pipe(prompt=prompt, generator=generator, guidance_scale=args.guidance_scale, **base_kwargs)
+                except TypeError as exc:
+                    if "guidance_scale" not in str(exc):
+                        raise
+                    pipe(prompt=prompt, generator=generator, **base_kwargs)
+
+    return forward_loop
+
+
+def _summarize_export(output_dir: Path) -> None:
+    cfg_path = output_dir / "transformer" / "config.json"
+    if not cfg_path.exists():
+        print(f"[warn] {cfg_path} missing.", file=sys.stderr)
+        return
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+    qc = cfg.get("quantization_config")
+    if not isinstance(qc, dict):
+        print("[warn] No quantization_config in transformer/config.json.", file=sys.stderr)
+        return
+    print("Export summary:")
+    print(f"  quant_method: {qc.get('quant_method')}")
+    print(f"  quant_algo:   {qc.get('quant_algo')}")
+    producer = qc.get("producer")
+    if isinstance(producer, dict):
+        print(f"  producer:     {producer.get('name')} {producer.get('version')}")
+    print(f"  config path:  {cfg_path}")
+
+
+def _force_export_quantized_weights(backbone: torch.nn.Module, dtype: torch.dtype) -> int:
+    """Convert in-memory weights of quantized modules to actual FP8 storage.
+
+    `export_hf_checkpoint` skips this step for unknown model types (HV-1.5 isn't
+    in ModelOpt's recognized-model registry), so we must call the per-weight
+    export helper ourselves. Same workaround as the HunyuanImage-3 calibration
+    helper.
+    """
+    from modelopt.torch.export.quant_utils import (
+        QUANTIZATION_NONE,
+        get_quantization_format,
+        quantizer_attr_names,
+        weight_attr_names,
+    )
+    from modelopt.torch.export.unified_export_hf import _export_quantized_weight
+
+    exported = 0
+    for name, module in backbone.named_modules():
+        try:
+            quantization_format = get_quantization_format(module)
+        except Exception as exc:
+            print(f"[warn] Could not inspect quantization format for {name}: {exc}", file=sys.stderr)
+            continue
+        if quantization_format == QUANTIZATION_NONE:
+            continue
+        for weight_name in weight_attr_names(module):
+            quantizer_attrs = quantizer_attr_names(weight_name)
+            weight_quantizer = getattr(module, quantizer_attrs.weight_quantizer, None)
+            if weight_quantizer is None or not getattr(weight_quantizer, "is_enabled", False):
+                continue
+            _export_quantized_weight(module, dtype, weight_name)
+            exported += 1
+    return exported
+
+
+def _hv15_quant_config_block(weight_block_size: list[int] | None = None) -> dict:
+    """Mirror ModelOpt FP8 metadata expected by vllm-omni's adapter (#2913).
+
+    Same shape as the HunyuanImage-3 author's _hunyuan_quant_config(). When
+    `weight_block_size` is given, advertise block-wise weight quantization in
+    the saved metadata (so consumers know to expect multi-element scale tensors).
+    """
+    weights_cfg: dict = {"dynamic": False, "num_bits": 8, "type": "float"}
+    if weight_block_size is not None:
+        weights_cfg["strategy"] = "block"
+        weights_cfg["block_structure"] = f"{weight_block_size[0]}x{weight_block_size[1]}"
+    return {
+        "config_groups": {
+            "group_0": {
+                "input_activations": {"dynamic": False, "num_bits": 8, "type": "float"},
+                "weights": weights_cfg,
+                "targets": ["Linear"],
+            }
+        },
+        "ignore": [
+            "context_embedder*",
+            "context_embedder_2*",
+            "cond_type_embed*",
+            "image_embedder*",
+            "norm1.linear*",
+            "norm1_context.linear*",
+            "norm2*",
+            "norm2_context*",
+            "norm_out*",
+            "proj_out*",
+            "time_embed*",
+            "token_refiner*",
+            "x_embedder*",
+        ],
+        "producer": {"name": "modelopt"},
+        "quant_algo": "FP8",
+        "quant_method": "modelopt",
+    }
+
+
+def _patch_quant_config(output_dir: Path, weight_block_size: list[int] | None = None) -> None:
+    """Inject quant_algo: FP8 + config_groups into transformer/config.json so
+    vllm-omni's adapter (#2913) recognises the checkpoint as ModelOpt FP8."""
+    cfg_path = output_dir / "transformer" / "config.json"
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+
+    new_qc = _hv15_quant_config_block(weight_block_size=weight_block_size)
+    existing = cfg.get("quantization_config")
+    if isinstance(existing, dict):
+        producer = existing.get("producer")
+        if isinstance(producer, dict):
+            new_qc["producer"] = producer
+
+    cfg["quantization_config"] = new_qc
+    with cfg_path.open("w", encoding="utf-8") as f:
+        json.dump(cfg, f, indent=2)
+
+
+def _save_pipeline_with_fp8_transformer(
+    pipe: DiffusionPipeline,
+    model_path: str,
+    output_dir: Path,
+    max_shard_size: str = "5GB",
+) -> None:
+    """Save the pipeline with the (now FP8) transformer.
+
+    Copies the source directory verbatim except for `transformer/`, then
+    saves the transformer with quantizers hidden so the state dict contains
+    only the FP8 weights + scale tensors.
+    """
+    from modelopt.torch.export.diffusers_utils import hide_quantizers_from_state_dict
+
+    src = Path(model_path)
+    if not src.exists():
+        from huggingface_hub import snapshot_download
+
+        src = Path(snapshot_download(model_path))
+
+    if output_dir.exists():
+        shutil.rmtree(output_dir)
+    shutil.copytree(src, output_dir, ignore=shutil.ignore_patterns("transformer"))
+
+    transformer_out = output_dir / "transformer"
+    # `hide_quantizers_from_state_dict` walks named_modules(); pass the actual
+    # nn.Module (transformer), not the diffusers Pipeline wrapper.
+    with hide_quantizers_from_state_dict(pipe.transformer):
+        pipe.transformer.save_pretrained(
+            str(transformer_out),
+            safe_serialization=True,
+            max_shard_size=max_shard_size,
+        )
+
+
+def main() -> None:
+    args = _build_parser().parse_args()
+    if not torch.cuda.is_available():
+        raise SystemExit("CUDA is required for ModelOpt FP8 quantization.")
+
+    mtq = _require_modelopt()
+    model_path, output_dir = _ensure_paths(args)
+    dtype = _select_dtype(args.dtype)
+    prompts = _build_prompts(args)
+
+    print("Quantization plan:")
+    weight_block_size = _parse_block_size(args.weight_block_size)
+
+    print(f"  input:           {args.model}")
+    print(f"  output:          {output_dir}")
+    print(f"  dtype:           {dtype}")
+    print(f"  height/width:    {args.height}x{args.width}")
+    print(f"  num_frames:      {args.num_frames}")
+    print(f"  calib_size:      {len(prompts)}")
+    print(f"  calib_steps:     {args.calib_steps}")
+    print(f"  quantize_mha:    {args.quantize_mha}")
+    print(
+        f"  weight strategy: {'block-wise ' + str(weight_block_size) if weight_block_size else 'per-tensor (default)'}"
+    )
+
+    pipe = _load_pipeline(model_path, dtype)
+    backbone = pipe.transformer
+
+    quant_config = copy.deepcopy(mtq.FP8_DEFAULT_CFG)
+    if weight_block_size is not None:
+        # Switch from per-tensor (default) to block-wise weight quantization.
+        # ModelOpt's wildcard "*weight_quantizer" matches every linear's weight quantizer.
+        quant_config["quant_cfg"]["*weight_quantizer"] = {
+            "num_bits": (4, 3),  # E4M3 (FP8 weights, same as default)
+            "block_sizes": {-1: weight_block_size[1], -2: weight_block_size[0]},
+        }
+        print(
+            f"  -> overriding weight quantizer with block_sizes={weight_block_size} "
+            f"({weight_block_size[0]}x{weight_block_size[1]} tiles)"
+        )
+
+    forward_loop = _build_forward_loop(pipe, args, prompts)
+    quantized = mtq.quantize(backbone, quant_config, forward_loop)
+    if quantized is not None:
+        pipe.transformer = quantized
+        backbone = quantized
+
+    _disable_known_problematic_quantizers(mtq, backbone, quantize_mha=args.quantize_mha)
+
+    print("\nForcing FP8 weight serialization (HV-1.5 isn't in ModelOpt's recognized-model registry,")
+    print("so we have to call the per-weight export helper ourselves)...")
+    exported = _force_export_quantized_weights(backbone, dtype)
+    print(f"  -> {exported} weights converted to FP8 in memory")
+    if exported == 0:
+        raise SystemExit(
+            "No quantized weights were exported. Calibration may have skipped every layer "
+            "(check the disable_quantizer regex) or `mtq.quantize` did not actually wrap any "
+            "weight quantizers."
+        )
+
+    print("\nSaving pipeline with FP8 transformer...")
+    _save_pipeline_with_fp8_transformer(pipe, model_path, output_dir)
+    _patch_quant_config(output_dir, weight_block_size=weight_block_size)
+    print(f"Saved to: {output_dir}")
+    _summarize_export(output_dir)
+
+    print("\nNext: validate the checkpoint with vllm-omni:")
+    print(
+        "  python examples/offline_inference/text_to_video/text_to_video.py \\\n"
+        f"    --model {output_dir} \\\n"
+        "    --quantization fp8 \\\n"
+        "    --prompt 'A dog running across a field of golden wheat.' \\\n"
+        f"    --height {args.height} --width {args.width} --num-frames {args.num_frames} \\\n"
+        "    --num-inference-steps 30 --guidance-scale 6.0 --seed 42 \\\n"
+        "    --output outputs/hv15_modelopt_fp8.mp4 \\\n"
+        "    --enforce-eager"
+    )
+    print(
+        "\n  (--quantization fp8 is auto-upgraded to ModelOpt FP8 at runtime because the "
+        "checkpoint's config.json has modelopt metadata.)"
+    )
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,471 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Quantize Wan2.2 (TI2V-5B, 704x1280 T2V) to a ModelOpt FP8 Hugging Face checkpoint.
+
+Calibrates the DiT transformer using a small video prompt set and exports a
+diffusers-style directory whose transformer carries ModelOpt FP8 metadata.
+The exported checkpoint is consumable by vllm-omni's ModelOpt FP8 adapter
+(see vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py).
+
+Layers kept full precision match the #2728 / #2795 pattern: condition embedder
+(time/text/image), patch embedding, modulation (scale_shift_table), final
+norm + proj_out, and sequence-parallel helpers. All attention + FFN linears
+are quantized — static calibration handles the numerics that online FP8
+couldn't (see #2920 ablation).
+
+Default target is `Wan-AI/Wan2.2-TI2V-5B-Diffusers`, the dense 5B variant that
+fits 80GB BF16. The A14B MoE variants need 2+ GPUs and are out of scope here.
+
+Example:
+    python examples/quantization/quantize_wan2_2_modelopt_fp8.py \\
+        --model Wan-AI/Wan2.2-TI2V-5B-Diffusers \\
+        --output ./wan22-ti2v-modelopt-fp8 \\
+        --overwrite
+"""
+
+from __future__ import annotations
+
+import argparse
+import copy
+import json
+import re
+import shutil
+import sys
+from pathlib import Path
+from typing import Any
+
+import torch
+from diffusers import DiffusionPipeline
+
+DEFAULT_PROMPTS = [
+    "A dog running across a field of golden wheat.",
+    "An astronaut riding a horse across the surface of Mars, red dust swirling, cinematic wide shot.",
+    "A hummingbird hovering in front of a vibrant red flower, slow motion, macro shot.",
+    "A crackling campfire at night under a starry sky, sparks rising into the dark.",
+    "An underwater shot of a coral reef with tropical fish swimming by, sun rays piercing the water.",
+    "A close-up of a blooming rose covered in morning dew, soft natural light.",
+    "A peaceful mountain village at dawn, mist rolling over the rooftops, cinematic establishing shot.",
+    "A skateboarder doing a kickflip in an urban plaza, slow motion, golden hour lighting.",
+]
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    p.add_argument("--model", required=True, help="Input Wan2.2 diffusers directory or HF id.")
+    p.add_argument("--output", required=True, help="Output directory for the ModelOpt FP8 checkpoint.")
+    p.add_argument("--dtype", choices=("bfloat16", "float16"), default="bfloat16")
+    p.add_argument("--height", type=int, default=704, help="Calibration video height (Wan2.2 TI2V-5B native: 704).")
+    p.add_argument("--width", type=int, default=1280, help="Calibration video width (Wan2.2 TI2V-5B native: 1280).")
+    p.add_argument(
+        "--num-frames",
+        type=int,
+        default=49,
+        help="Frames per calibration sample. 49 matches the typical short benchmark; "
+        "use 17 to reduce memory pressure during calibration.",
+    )
+    p.add_argument("--guidance-scale", type=float, default=5.0)
+    p.add_argument(
+        "--calib-steps",
+        type=int,
+        default=10,
+        help="Denoising steps per calibration prompt (10 is enough for amax statistics).",
+    )
+    p.add_argument("--calib-size", type=int, default=8, help="How many prompts to use for calibration.")
+    p.add_argument("--seed", type=int, default=42)
+    p.add_argument(
+        "--prompt",
+        action="append",
+        default=[],
+        help="Custom calibration prompt. Repeat to provide multiple.",
+    )
+    p.add_argument(
+        "--quantize-mha",
+        action="store_true",
+        help="Enable FP8 attention K/V/softmax quantizers. Off by default — Wan2.2's long attention "
+        "sequences amplified FP8 drift in the online ablation (see #2920).",
+    )
+    p.add_argument(
+        "--weight-block-size",
+        type=str,
+        default=None,
+        help="Per-block weight quantization as 'M,N' (e.g. '128,128'). Default per-tensor. "
+        "Note: vllm-omni's ModelOpt adapter may not yet dispatch block-wise scales — check #2924 "
+        "for the HV-1.5 investigation status before relying on this.",
+    )
+    p.add_argument("--overwrite", action="store_true", help="Replace an existing output directory.")
+    return p
+
+
+def _parse_block_size(spec: str | None) -> list[int] | None:
+    if spec is None:
+        return None
+    parts = [int(x) for x in spec.split(",") if x.strip()]
+    if len(parts) != 2:
+        raise SystemExit(f"--weight-block-size must be 'M,N' (2 ints), got {spec!r}")
+    return parts
+
+
+def _require_modelopt() -> Any:
+    try:
+        import modelopt.torch.quantization as mtq
+    except ModuleNotFoundError as exc:
+        raise SystemExit(
+            "NVIDIA ModelOpt is not installed. Install with:\n"
+            "  pip install 'nvidia-modelopt[all]'\n"
+            f"Original error: {exc}"
+        ) from exc
+    return mtq
+
+
+def _ensure_paths(args: argparse.Namespace) -> tuple[str, Path]:
+    model_path = args.model
+    output_dir = Path(args.output).expanduser().resolve()
+    if output_dir.exists():
+        if not args.overwrite:
+            raise SystemExit(f"Output directory already exists: {output_dir}\nPass --overwrite to replace it.")
+        shutil.rmtree(output_dir)
+    return model_path, output_dir
+
+
+def _select_dtype(name: str) -> torch.dtype:
+    return {"bfloat16": torch.bfloat16, "float16": torch.float16}[name]
+
+
+def _build_prompts(args: argparse.Namespace) -> list[str]:
+    prompts = args.prompt or DEFAULT_PROMPTS
+    if args.calib_size <= 0:
+        raise SystemExit("--calib-size must be positive.")
+    if len(prompts) < args.calib_size:
+        repeats = (args.calib_size + len(prompts) - 1) // len(prompts)
+        prompts = (prompts * repeats)[: args.calib_size]
+    return prompts[: args.calib_size]
+
+
+# Layers to KEEP at full precision. Wan2.2's module naming:
+# - condition_embedder: time_embedder, time_proj, text_embedder, image_embedder (I2V)
+# - patch_embedding: Conv3dLayer (already not Linear, belt-and-suspenders skip)
+# - scale_shift_table: nn.Parameter modulation (not Linear, but pattern guard)
+# - norm_out: AdaLayerNorm final
+# - proj_out: final nn.Linear
+# - timestep_proj_prepare / output_scale_shift_prepare: SP helpers
+def _filter_func_wan22(name: str) -> bool:
+    pattern = re.compile(
+        r"(proj_out.*|"
+        r".*(condition_embedder|patch_embedding|"
+        r"norm_out|scale_shift_table|"
+        r"timestep_proj_prepare|output_scale_shift_prepare).*)"
+    )
+    return pattern.match(name) is not None
+
+
+def _mha_filter_func(name: str) -> bool:
+    pattern = re.compile(
+        r".*(q_bmm_quantizer|k_bmm_quantizer|v_bmm_quantizer|softmax_quantizer|bmm2_output_quantizer).*"
+    )
+    return pattern.match(name) is not None
+
+
+def _disable_known_problematic_quantizers(mtq: Any, backbone: torch.nn.Module, *, quantize_mha: bool) -> None:
+    if not hasattr(mtq, "disable_quantizer"):
+        return
+    mtq.disable_quantizer(backbone, _filter_func_wan22)
+    if not quantize_mha:
+        mtq.disable_quantizer(backbone, _mha_filter_func)
+
+
+def _load_pipeline(model_path: str, dtype: torch.dtype) -> DiffusionPipeline:
+    pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=dtype)
+    if hasattr(pipe, "set_progress_bar_config"):
+        pipe.set_progress_bar_config(disable=True)
+    pipe.to("cuda")
+    return pipe
+
+
+def _build_forward_loop(pipe: DiffusionPipeline, args: argparse.Namespace, prompts: list[str]):
+    generator = torch.Generator(device="cuda")
+
+    # Try setting guidance on the pipeline's guider if present (newer diffusers APIs).
+    guider = getattr(pipe, "guider", None)
+    if guider is not None and hasattr(guider, "guidance_scale"):
+        try:
+            guider.guidance_scale = args.guidance_scale
+        except Exception:
+            pass
+
+    base_kwargs = dict(
+        height=args.height,
+        width=args.width,
+        num_frames=args.num_frames,
+        num_inference_steps=args.calib_steps,
+        output_type="latent",
+    )
+
+    def forward_loop(*_unused_args, **_unused_kwargs) -> None:
+        with torch.inference_mode():
+            for idx, prompt in enumerate(prompts):
+                generator.manual_seed(args.seed + idx)
+                # Try with guidance_scale first; fall back without on TypeError
+                # for pipelines that take CFG via guider config only.
+                try:
+                    pipe(prompt=prompt, generator=generator, guidance_scale=args.guidance_scale, **base_kwargs)
+                except TypeError as exc:
+                    if "guidance_scale" not in str(exc):
+                        raise
+                    pipe(prompt=prompt, generator=generator, **base_kwargs)
+
+    return forward_loop
+
+
+def _summarize_export(output_dir: Path) -> None:
+    cfg_path = output_dir / "transformer" / "config.json"
+    if not cfg_path.exists():
+        print(f"[warn] {cfg_path} missing.", file=sys.stderr)
+        return
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+    qc = cfg.get("quantization_config")
+    if not isinstance(qc, dict):
+        print("[warn] No quantization_config in transformer/config.json.", file=sys.stderr)
+        return
+    print("Export summary:")
+    print(f"  quant_method: {qc.get('quant_method')}")
+    print(f"  quant_algo:   {qc.get('quant_algo')}")
+    producer = qc.get("producer")
+    if isinstance(producer, dict):
+        print(f"  producer:     {producer.get('name')} {producer.get('version')}")
+    print(f"  config path:  {cfg_path}")
+
+
+def _force_export_quantized_weights(backbone: torch.nn.Module, dtype: torch.dtype) -> int:
+    """Convert in-memory weights of quantized modules to actual FP8 storage.
+
+    `export_hf_checkpoint` skips this step for unknown model types (Wan2.2 isn't
+    in ModelOpt's recognized-model registry), so we must call the per-weight
+    export helper ourselves. Same workaround as the HunyuanVideo-1.5 / HunyuanImage-3
+    calibration helpers.
+    """
+    from modelopt.torch.export.quant_utils import (
+        QUANTIZATION_NONE,
+        get_quantization_format,
+        quantizer_attr_names,
+        weight_attr_names,
+    )
+    from modelopt.torch.export.unified_export_hf import _export_quantized_weight
+
+    exported = 0
+    for name, module in backbone.named_modules():
+        try:
+            quantization_format = get_quantization_format(module)
+        except Exception as exc:
+            print(f"[warn] Could not inspect quantization format for {name}: {exc}", file=sys.stderr)
+            continue
+        if quantization_format == QUANTIZATION_NONE:
+            continue
+        for weight_name in weight_attr_names(module):
+            quantizer_attrs = quantizer_attr_names(weight_name)
+            weight_quantizer = getattr(module, quantizer_attrs.weight_quantizer, None)
+            if weight_quantizer is None or not getattr(weight_quantizer, "is_enabled", False):
+                continue
+            _export_quantized_weight(module, dtype, weight_name)
+            exported += 1
+    return exported
+
+
+def _wan22_quant_config_block(weight_block_size: list[int] | None = None) -> dict:
+    """Mirror ModelOpt FP8 metadata expected by vllm-omni's adapter (#2913)."""
+    weights_cfg: dict = {"dynamic": False, "num_bits": 8, "type": "float"}
+    if weight_block_size is not None:
+        weights_cfg["strategy"] = "block"
+        weights_cfg["block_structure"] = f"{weight_block_size[0]}x{weight_block_size[1]}"
+    return {
+        "config_groups": {
+            "group_0": {
+                "input_activations": {"dynamic": False, "num_bits": 8, "type": "float"},
+                "weights": weights_cfg,
+                "targets": ["Linear"],
+            }
+        },
+        "ignore": [
+            "condition_embedder*",
+            "norm_out*",
+            "output_scale_shift_prepare*",
+            "patch_embedding*",
+            "proj_out*",
+            "scale_shift_table*",
+            "timestep_proj_prepare*",
+        ],
+        "producer": {"name": "modelopt"},
+        "quant_algo": "FP8",
+        "quant_method": "modelopt",
+    }
+
+
+def _patch_quant_config(output_dir: Path, weight_block_size: list[int] | None = None) -> None:
+    """Inject quant_algo: FP8 + config_groups into each transformer's config.json
+    so vllm-omni's adapter (#2913) recognises the checkpoint as ModelOpt FP8.
+
+    Patches both ``transformer`` and ``transformer_2`` (A14B) when present."""
+    for sub in ("transformer", "transformer_2"):
+        cfg_path = output_dir / sub / "config.json"
+        if not cfg_path.exists():
+            continue
+        with cfg_path.open(encoding="utf-8") as f:
+            cfg = json.load(f)
+
+        new_qc = _wan22_quant_config_block(weight_block_size=weight_block_size)
+        existing = cfg.get("quantization_config")
+        if isinstance(existing, dict):
+            producer = existing.get("producer")
+            if isinstance(producer, dict):
+                new_qc["producer"] = producer
+
+        cfg["quantization_config"] = new_qc
+        with cfg_path.open("w", encoding="utf-8") as f:
+            json.dump(cfg, f, indent=2)
+
+
+def _list_transformers(pipe: DiffusionPipeline) -> list[tuple[str, torch.nn.Module]]:
+    """Return [(attr_name, module)] for every DiT on the pipeline.
+
+    Wan2.2 A14B has both ``transformer`` (low-noise) and ``transformer_2``
+    (high-noise). TI2V-5B has only ``transformer``.
+    """
+    out = []
+    for attr in ("transformer", "transformer_2"):
+        mod = getattr(pipe, attr, None)
+        if mod is not None:
+            out.append((attr, mod))
+    return out
+
+
+def _save_pipeline_with_fp8_transformer(
+    pipe: DiffusionPipeline,
+    model_path: str,
+    output_dir: Path,
+    max_shard_size: str = "5GB",
+) -> None:
+    """Copy source dir verbatim minus transformer dirs, then save each quantized DiT.
+
+    Handles A14B's dual transformer (``transformer`` + ``transformer_2``) as well
+    as the single-DiT TI2V-5B.
+    """
+    from modelopt.torch.export.diffusers_utils import hide_quantizers_from_state_dict
+
+    src = Path(model_path)
+    if not src.exists():
+        from huggingface_hub import snapshot_download
+
+        src = Path(snapshot_download(model_path))
+
+    if output_dir.exists():
+        shutil.rmtree(output_dir)
+    shutil.copytree(src, output_dir, ignore=shutil.ignore_patterns("transformer", "transformer_2"))
+
+    for attr, backbone in _list_transformers(pipe):
+        transformer_out = output_dir / attr
+        # Pass the nn.Module (transformer), not the Pipeline wrapper.
+        with hide_quantizers_from_state_dict(backbone):
+            backbone.save_pretrained(
+                str(transformer_out),
+                safe_serialization=True,
+                max_shard_size=max_shard_size,
+            )
+
+
+def main() -> None:
+    args = _build_parser().parse_args()
+    if not torch.cuda.is_available():
+        raise SystemExit("CUDA is required for ModelOpt FP8 quantization.")
+
+    mtq = _require_modelopt()
+    model_path, output_dir = _ensure_paths(args)
+    dtype = _select_dtype(args.dtype)
+    prompts = _build_prompts(args)
+    weight_block_size = _parse_block_size(args.weight_block_size)
+
+    print("Quantization plan:")
+    print(f"  input:           {args.model}")
+    print(f"  output:          {output_dir}")
+    print(f"  dtype:           {dtype}")
+    print(f"  height/width:    {args.height}x{args.width}")
+    print(f"  num_frames:      {args.num_frames}")
+    print(f"  calib_size:      {len(prompts)}")
+    print(f"  calib_steps:     {args.calib_steps}")
+    print(f"  quantize_mha:    {args.quantize_mha}")
+    print(
+        f"  weight strategy: {'block-wise ' + str(weight_block_size) if weight_block_size else 'per-tensor (default)'}"
+    )
+
+    pipe = _load_pipeline(model_path, dtype)
+    transformers = _list_transformers(pipe)
+    if not transformers:
+        raise SystemExit("Pipeline has no transformer or transformer_2 attribute.")
+    print(f"  found {len(transformers)} transformer(s): {', '.join(a for a, _ in transformers)}")
+
+    quant_config = copy.deepcopy(mtq.FP8_DEFAULT_CFG)
+    if weight_block_size is not None:
+        quant_config["quant_cfg"]["*weight_quantizer"] = {
+            "num_bits": (4, 3),
+            "block_sizes": {-1: weight_block_size[1], -2: weight_block_size[0]},
+        }
+        print(
+            f"  -> overriding weight quantizer with block_sizes={weight_block_size} "
+            f"({weight_block_size[0]}x{weight_block_size[1]} tiles)"
+        )
+
+    forward_loop = _build_forward_loop(pipe, args, prompts)
+
+    # Quantize each DiT. The forward_loop runs the full pipeline, so quantizers
+    # on every attached transformer (A14B: transformer + transformer_2) get
+    # calibrated during the same passes.
+    for attr, backbone in transformers:
+        print(f"\nQuantizing {attr}...")
+        quantized = mtq.quantize(backbone, quant_config, forward_loop)
+        if quantized is not None:
+            setattr(pipe, attr, quantized)
+        _disable_known_problematic_quantizers(mtq, getattr(pipe, attr), quantize_mha=args.quantize_mha)
+
+    # Export weights to FP8 only AFTER all transformers are calibrated. Exporting
+    # inside the loop would convert transformer's weights to real FP8, and the
+    # next transformer's forward_loop (full pipeline) would then fake-quantize an
+    # already-FP8 weight -> "fake_e4m3fy not implemented for Float8_e4m3fn".
+    print("\nForcing FP8 weight serialization (Wan2.2 isn't in ModelOpt's recognized-model registry,")
+    print("so we have to call the per-weight export helper ourselves)...")
+    total_exported = 0
+    for attr, backbone in _list_transformers(pipe):
+        exported = _force_export_quantized_weights(backbone, dtype)
+        print(f"  -> {exported} weights converted to FP8 in {attr}")
+        total_exported += exported
+
+    if total_exported == 0:
+        raise SystemExit(
+            "No quantized weights were exported. Calibration may have skipped every layer "
+            "(check the disable_quantizer regex) or `mtq.quantize` did not actually wrap any "
+            "weight quantizers."
+        )
+
+    print("\nSaving pipeline with FP8 transformer(s)...")
+    _save_pipeline_with_fp8_transformer(pipe, model_path, output_dir)
+    _patch_quant_config(output_dir, weight_block_size=weight_block_size)
+    print(f"Saved to: {output_dir}")
+    _summarize_export(output_dir)
+
+    print("\nNext: validate the checkpoint with vllm-omni:")
+    print(
+        "  python examples/offline_inference/text_to_video/text_to_video.py \\\n"
+        f"    --model {output_dir} \\\n"
+        "    --quantization fp8 \\\n"
+        "    --prompt 'A dog running across a field of golden wheat.' \\\n"
+        f"    --height {args.height} --width {args.width} --num-frames {args.num_frames} \\\n"
+        "    --num-inference-steps 30 --guidance-scale 5.0 --seed 42 \\\n"
+        "    --output outputs/wan22_modelopt_fp8.mp4"
+    )
+    print(
+        "\n  (--quantization fp8 is auto-upgraded to ModelOpt FP8 at runtime because the "
+        "checkpoint's config.json has modelopt metadata.)"
+    )
+
+
+if __name__ == "__main__":
+    main()
@@ -1,346 +0,0 @@
-# MiniMax-H3 on RTX PRO 6000 Blackwell GPUs
-
-This recipe runs MiniMax-H3 in BF16 on 96 GiB RTX PRO 6000 Blackwell GPUs.
-The additional HBM over the RTX PRO 5000 profile removes the four-GPU
-minimum: two GPUs are enough to keep the model resident with TP2. Four and
-eight GPUs raise the Ulysses degree to shard the attention sequence further.
-CPU offload and distributed layerwise offload are not required in any of
-these configurations.
-
-Validated on:
- Host: YLX Y762
- GPUs: 8 × RTX PRO 6000 Blackwell (96 GiB)
- Device order: default (`CUDA_VISIBLE_DEVICES` not set)
- Driver / CUDA: 580.105.08 / 13.0
- Container image: `vllm/vllm-omni:minimax-h3`
- Workload: T2VA, 1344×768, `duration=5.0`, 50 steps, `flow_shift=12`, `seed=1101`
-
-## Capacity requirements
-
-| Resource | Two GPUs | Four GPUs | Eight GPUs |
-| --- | ---: | ---: | ---: |
-| GPU HBM | 96 GiB per GPU | 96 GiB per GPU | 96 GiB per GPU |
-| Checkpoint storage | 135 GiB per partition | 135 GiB per partition | 135 GiB per partition |
-| Available system RAM | 200 GiB minimum | 200 GiB minimum | 200 GiB minimum |
-| Recommended system RAM | 384 GiB | 384 GiB | 384 GiB |
-| Measured peak HBM per GPU | 77.49 GiB | 66.44 GiB | 61.07 GiB |
-
-`FL2VA` and `Ref2VA` are separate checkpoint partitions. Start one server at
-a time on a host sized for the minimum system-memory requirement, or pass
-`--task-type fl2va` or `--task-type ref2va` to download and load a single
-partition. The two-server layout described in the eight-GPU section doubles
-both the storage and the host-memory requirement.
-
-## Parallelism summary
-
-| Configuration | TP | Ulysses | Text-encoder TP | VAE patch parallel |
-| --- | ---: | ---: | ---: | ---: |
-| Two GPUs | 2 | 1 | 2 | 2 |
-| Four GPUs | 2 | 2 | 4 | 4 |
-| Eight GPUs | 2 | 4 | 8 | 8 |
-| Eight GPUs, headroom variant | 4 | 2 | 8 | 8 |
-
-Per-GPU weight residency is set by the tensor-parallel degree alone. Raising
-the Ulysses degree lowers activation memory and per-step latency but leaves
-weight residency unchanged. Ring parallelism stays at 1, and H3 is
-CFG-distilled, so `--cfg-parallel-size` must also remain 1.
-
-## PCIe topology and GPU order
-
-RTX PRO 6000 Blackwell does not provide NVLink. Before starting the server,
-inspect the host topology:
-
-```bash
-nvidia-smi topo -m
-nvidia-smi nvlink -s
-```
-
-Tensor-parallel groups are consecutive ranks. Ulysses groups are strided by
-the tensor-parallel degree. Confirm this grouping against the server log
-before tuning the device order on a new host.
-
-For the two-GPU configuration, pick a single `PXB` pair on one NUMA node.
-For the four-GPU configuration, pick two `PXB` pairs on the same node and
-order them so that each Ulysses group lands inside one pair. If physical
-GPUs `(0,1)` and `(2,3)` are the two local pairs, the order is
-`CUDA_VISIBLE_DEVICES=0,2,1,3`. Do not copy these IDs blindly: reproduce the
-same relationship on the target host.
-
-Device-order pinning and NUMA binding are tuning knobs, not prerequisites.
-The measurements in this recipe were taken without either, so any gain from
-them is additional to the numbers reported below and is host-specific.
-
-## Two-GPU serving configuration
-
-Two 96 GiB GPUs hold the BF16 model with TP2 alone. There is no Ulysses
-group, so the DiT attention sequence is not sharded and activation memory is
-higher than in the four-GPU profile at the same output shape. Re-measure
-peak memory before increasing the output shape, the reference-input length,
-or concurrency.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8000
-
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 2 \
-  --tensor-parallel-size 2 \
-  --usp 1 \
-  --ring 1 \
-  --text-encoder-tp-size 2 \
-  --vae-patch-parallel-size 2 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-## Four-GPU serving configuration
-
-Four GPUs keep TP2 for the weight shard and add Ulysses2, which shards the
-attention sequence and lowers per-GPU activation memory. Text-encoder TP4
-and VAE patch parallelism 4 spread the Qwen3-VL encoder and tiled decode
-across all four GPUs. TP1 is not an option on this card: an unsharded BF16
-partition does not fit in 96 GiB.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8000
-
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 4 \
-  --tensor-parallel-size 2 \
-  --usp 2 \
-  --ring 1 \
-  --text-encoder-tp-size 4 \
-  --vae-patch-parallel-size 4 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-## Eight-GPU serving configuration
-
-Eight GPUs extend the Ulysses degree to 4 while keeping TP2. This does not
-lower per-GPU weight residency relative to the four-GPU profile; it lowers
-activation memory and per-step latency by sharding the attention sequence
-four ways.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8000
-
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 8 \
-  --tensor-parallel-size 2 \
-  --usp 4 \
-  --ring 1 \
-  --text-encoder-tp-size 8 \
-  --vae-patch-parallel-size 8 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-### Rank ordering across two sockets
-
-With TP2 and Ulysses4 the two Ulysses groups are ranks `(0,2,4,6)` and
-`(1,3,5,7)`, and the four tensor-parallel pairs are `(0,1)`, `(2,3)`,
-`(4,5)`, and `(6,7)`. On a dual-socket host these two collectives cannot
-both be socket-local. If you choose to pin the device order, the trade-off
-is:
-
-| Device order | Socket-local collective | Crosses sockets |
-| --- | --- | --- |
-| `0,4,1,5,2,6,3,7` | Ulysses all-to-all | TP all-reduce |
-| `0,1,2,3,4,5,6,7` | TP all-reduce | Ulysses all-to-all |
-
-The first order assumes physical GPUs `0-3` are on NUMA node 0 and `4-7` on
-node 1. Reproduce that relationship on the target host rather than copying
-the IDs. The reported measurements use the default order and no NUMA
-binding; the two orders were not compared on this host.
-
-### Headroom variant: TP4 with Ulysses2
-
-Raising the tensor-parallel degree to 4 halves per-GPU weight residency and
-leaves room for long Ref2VA references, larger output shapes, or
-concurrency greater than one. It also adds a four-way all-reduce per DiT
-block over a link without NVLink. Use it when the TP2 profile runs out of
-headroom, not as the default. Replace the parallel flags above with:
-
-```bash
-  --tensor-parallel-size 4 \
-  --usp 2 \
-```
-
-### Two independent four-GPU servers
-
-An eight-GPU host can instead run one FL2VA server and one Ref2VA server
-side by side, each pinned to its own NUMA node with the four-GPU
-configuration. This removes every cross-socket collective and lifts the
-one-server-at-a-time restriction, at the cost of doubling the requirements
-to 400 GiB available system RAM and 270 GiB of model storage.
-
-Use `CUDA_VISIBLE_DEVICES=0,2,1,3`, `--cpunodebind=0 --membind=0`, and
-`--port 8091` for the FL2VA server. Use `CUDA_VISIBLE_DEVICES=4,6,5,7`,
-`--cpunodebind=1 --membind=1`, and `--port 8092` for the Ref2VA server.
-This layout is described for completeness and was not part of the measured
-runs.
-
-## Shared serving notes
-
-Do not add `--enforce-eager` for a performance run. Warm the server before
-measuring so regional compilation is outside the measured request. On this
-host the first request after startup ran 19% slower than the steady state
-(107.58 s versus 90.48 s on eight GPUs); two warmup requests were enough to
-converge.
-
-For Ref2VA on a single-server layout, stop the FL2VA server and restart the
-same command with `MODEL="${MODEL_ROOT}/Ref2VA"`.
-
-## Attention backend
-
-RTX PRO 6000 Blackwell is an SM120 part, so the datacenter-Blackwell
-`TRTLLM_ATTN` default does not apply here. Every configuration above selects
-cuDNN BF16 attention explicitly. This keeps the recipe independent of
-platform-default backend changes and does not depend on the experimental
-SM120 kernel.
-
-## Optional: online FP8
-
-`--quantization fp8` quantizes eligible DiT linears at load time and is
-compatible with tensor parallelism and VAE tiling. Use it when the resident
-BF16 peak leaves too little headroom for long Ref2VA references, a larger
-output shape, or concurrency greater than one. It cannot be combined with
-layerwise offload.
-
-## Target-hardware validation
-
-T2VA, 1344×768, `duration=5.0`, `fps=24`, 50 steps, `flow_shift=12`,
-`seed=1101`, BF16, `CUDNN_ATTN`, tiled VAE, one request at a time. Servers
-were started with the commands above — default device order, no NUMA
-binding — plus `--enable-diffusion-pipeline-profiler`. Two warmup requests
-preceded each measured request.
-
-| Measurement | Two GPUs | Four GPUs | Eight GPUs |
-| --- | ---: | ---: | ---: |
-| Topology | TP2 × USP1 | TP2 × USP2 | TP2 × USP4 |
-| Text encode | 0.040 s | 0.044 s | 0.035 s |
-| Denoise, 50 steps | 278.55 s | 168.73 s | 87.90 s |
-| Per step | 5.571 s | 3.375 s | 1.758 s |
-| VAE decode | 5.396 s | 2.791 s | 1.798 s |
-| Client E2E | 284.76 s | 172.32 s | 90.48 s |
-| Peak HBM per GPU | 77.49 GiB | 66.44 GiB | 61.07 GiB |
-| Headroom below 96 GiB | 18.5 GiB | 29.6 GiB | 34.9 GiB |
-
-Stage times are read from the `X-Stage-Durations` response header of
-`/v1/videos/sync`. Peak memory is the maximum of `nvidia-smi
--query-gpu=memory.used` sampled at 1 Hz across every device for the
-duration of the measured request. Per step is denoise wall time divided by
-the 50 requested steps. Stage times sum to roughly 0.75 s less than
-end-to-end in all three configurations; queueing, result transfer, and MP4
-muxing sit outside the profiled stages.
-
-### Scaling behaviour
-
-Denoise speedup is not uniform across the sweep: 1.65× from two to four
-GPUs (83% efficiency) but 1.92× from four to eight (96%). Two GPUs run
-Ulysses1, so there is no sequence parallelism at all; going to four GPUs
-pays the one-time cost of introducing the all-to-all, while going from four
-to eight only widens an all-to-all that already exists. Expect the second
-doubling to pay off better than the first on this topology.
-
-VAE decode behaves in the opposite direction — 1.93× from two to four GPUs
-but only 1.55× from four to eight — as patch parallelism produces smaller
-tiles and tile-boundary overhead grows.
-
-Text encoding is 0.04 s in every configuration and is not worth optimising;
-denoise is 96-98% of end-to-end throughout.
-
-### Per-GPU memory model
-
-Peak memory falls by 11.05 GiB from two to four GPUs and by a further
-5.37 GiB from four to eight — halving each time the Ulysses degree doubles,
-because all three configurations shard the DiT with TP2 and hold identical
-weights per GPU. Fitting the first two points gives:
-
-```
-peak HBM per GPU ≈ 55.4 GiB + 22.1 GiB / ulysses_degree
-```
-
-That fit predicts 60.9 GiB at Ulysses4 against 61.07 GiB measured, a 0.25%
-error. The practical consequence is a floor near 55 GiB per GPU: adding
-GPUs past eight will not reduce the per-GPU requirement further. To serve
-on smaller cards, raise the tensor-parallel degree instead.
-
-Re-measure memory for longer reference inputs, concurrency greater than
-one, or a different output shape.
-
-### Not yet measured
-
-Ref2VA latency and memory have not been measured on this host. Ref2VA
-drives the Qwen3-VL presentation from tens of tokens for text-only prompts
-to several thousand with image or video references, so T2VA numbers do not
-transfer to it. The eight-GPU device-order comparison in the section above
-was also not run.
-
-## T2VA request example
-
-`t2va` requires an explicit `aspect_ratio` even when `width` and `height`
-are supplied.
-
-```bash
-export API_URL="http://127.0.0.1:${PORT}/v1/videos/sync"
-
-curl -sS --max-time 1800 -X POST "${API_URL}" \
-  -F 'prompt=At night, three cats march into a bedroom playing tiny brass instruments, then abruptly file out, with synchronized room ambience.' \
-  -F 'width=1344' \
-  -F 'height=768' \
-  -F 'aspect_ratio=16:9' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=50' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":5.0,"audio_flow_shift":3.0}' \
-  -o t2va.mp4
-```
-
-To collect the stage breakdown and peak memory for a request, add
-`--enable-diffusion-pipeline-profiler` to the server command and `-D
-headers.txt` to the curl invocation, then read `X-Stage-Durations` and
-`X-Peak-Memory-MB` from the saved headers.
-
-## Ref2VA request example
-
-`ref2va` defaults to a 16:9 aspect ratio, so `aspect_ratio` is optional
-here.
-
-```bash
-curl -X POST "http://127.0.0.1:${PORT}/v1/videos/sync" \
-  --fail-with-body -w '\nHTTP %{http_code}\n' \
-  --max-time 1200 \
-  -F "input_reference=@/root/hand.jpg;type=image/jpeg" \
-  -F "audio_reference=</root/audio_ref.json" \
-  -F "prompt=2D动画融合在一起的影像。夕阳余晖残留在窗边，生活感十足的小厨房里有旧木桌、洗到一半的马克杯、起雾的玻璃瓶、悬挂的抹布。画面带有智能手机单手拍摄的手抖、近距离对焦的犹豫、逆光曝光波动。要像在家中慌忙拍下某个不可思议事件的自然质感，不要广告影像的精心整理。声音只用厨房环境声与手绘生物柔和的电子音、小小的叫声。" \
-  -F 'width=1344' -F 'height=768' -F 'fps=24' \
-  -F 'num_inference_steps=60' -F 'flow_shift=12' -F 'seed=1101' \
-  -F 'extra_params={"task":"ref2va","duration":8,"audio_flow_shift":3.0}' \
-  -o /root/out_ref2va.mp4
-```
@@ -1,262 +0,0 @@
-# MiniMax-H3 on DGX Spark (GB10)
-
-This recipe uses online FP8 weight quantization, tiled VAE decode, and a single
-resident partition. GB10 is a unified-memory platform, so unlike the discrete-GPU
-recipes it uses **no offload of any kind** — see the capacity note below.
-
-Validated on:
-
- Host: DGX Spark (GB10), aarch64
- GPUs: 1 (unified memory)
- Driver: <FILL_DRIVER_VERSION>
- vLLM: 0.26.0
- vLLM-Omni: `main` at `e1aa6eae75c460cd1893bc320546e81e66973831`
- Workloads: T2VA and Ref2VA, 960x576, `duration=8.0`, 50 steps, `flow_shift=12`,
-  `seed=1101`
-
-
-## Capacity requirements
-
-| Resource | DGX Spark (GB10) |
-| --- | ---: |
-| Unified memory | 128 GB LPDDR5X (~121 GiB usable) |
-| GPUs | 1 |
-| Checkpoint storage | 135 GiB per partition |
-| Measured peak allocator high-water, T2VA (FP8) | 97.7 GiB |
-| Measured peak allocator high-water, Ref2VA (FP8) | 102.8 GiB |
-
-`FL2VA` and `Ref2VA` are separate 135 GiB checkpoint partitions. Start one server
-at a time.
-
-On GB10 the CPU and GPU share one physical memory pool, which changes the capacity
-math relative to the RTX and datacenter recipes:
-
- **Do not use `--enable-distributed-layerwise-offload`.** DLO stages rank-local
-  weights into pinned host memory, which on GB10 is the same pool the weights are
-  already in. Peak usage roughly doubles and the process is killed by the OOM
-  killer (`Exit code: -9`) shortly after `Enabling offloader backend`.
- **Do not use `--enable-cpu-offload`.** Moving weights from "VRAM" to "host RAM"
-  frees nothing here.
- **`--quantization fp8` is mandatory.** A BF16 partition is 135 GiB and does not
-  fit in 121 GiB. Online FP8 quantizes the DiT only (62 GiB to ~31 GiB); the
-  Qwen3-VL text encoder and both VAEs stay BF16.
-
-With ~97.7 GiB of the pool held by the allocator at peak, T2VA leaves roughly
-23 GiB of headroom for the OS, page cache, and any other process on the box.
-Ref2VA is tighter on both counts. The allocator high-water rises to 102.8 GiB,
-and the allocator figure understates true pool usage.
-
-Sampling `/proc/meminfo` at 1 Hz across a 50-step Ref2VA request on a host with
-`MemTotal: 127600524 kB` (121.7 GiB), `MemAvailable` started at 8.1 GiB, fell to
-a trough of **7.4 GiB**, and recovered to 8.9 GiB. At the trough the pool held
-roughly **114.3 GiB** — 11.4 GiB more than the 102.8 GiB the allocator reports,
-which is the CUDA context, non-PyTorch allocations, and page cache the header
-does not count.
-
-Treat this platform as strictly single-tenant for Ref2VA. There is no room for a
-second process, and adding reference images, reference videos, or a larger output
-shape will run into the OOM killer.
-
-## One GB10: 960x576, 8 seconds
-
-```bash
-CUDA_VISIBLE_DEVICES=0 \
-FLASHINFER_DISABLE_VERSION_CHECK=1 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=7200 \
-vllm serve /path/to/MiniMax-H3/FL2VA \
-  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
-  --init-timeout 3600 \
-  --num-gpus 1 --tensor-parallel-size 1 --text-encoder-tp-size 1 \
-  --usp 1 --ring 1 --vae-patch-parallel-size 1 \
-  --vae-parallel-mode tile --vae-use-tiling \
-  --quantization fp8 --enforce-eager \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-Wait for `Application startup complete`, then run a short smoke test before
-committing to a full 50-step request.
-
-`t2va` requires an explicit `aspect_ratio` even when `width` and `height` are
-supplied; omitting it fails the request with
-`OmniClientError: t2va requires an explicit aspect_ratio`.
-
-```bash
-curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
-  -F 'prompt=At night, three cats march into a bedroom playing tiny brass instruments, then abruptly file out, with synchronized room ambience.' \
-  -F 'width=960' \
-  -F 'height=576' \
-  -F 'aspect_ratio=16:9' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=10' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":4.0,"audio_flow_shift":3.0}' \
-  -o h3-gb10-smoke.mp4
-```
-
-The full-quality request uses 50 steps:
-
-```bash
-curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
-  -F 'prompt=At night, three cats march into a bedroom playing tiny brass instruments, then abruptly file out, with synchronized room ambience.' \
-  -F 'width=960' \
-  -F 'height=576' \
-  -F 'aspect_ratio=16:9' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=50' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":8.0,"audio_flow_shift":3.0}' \
-  -o h3-gb10-t2va.mp4
-
-ffprobe -v error -show_entries \
-  stream=index,codec_name,width,height,r_frame_rate,sample_rate,channels \
-  -of json h3-gb10-t2va.mp4
-```
-
-Both requests return `200 OK` with an MP4 body: H.264 video at the requested
-geometry plus a 32 kHz stereo AAC track.
-
-## One GB10: Ref2VA, 960x576, 8 seconds
-
-`FL2VA` and `Ref2VA` are separate 135 GiB partitions and only one fits at a time.
-Stop the FL2VA server before starting this one.
-
-```bash
-CUDA_VISIBLE_DEVICES=0 \
-FLASHINFER_DISABLE_VERSION_CHECK=1 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400 \
-vllm serve /path/to/MiniMax-H3/Ref2VA \
-  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
-  --init-timeout 3600 \
-  --num-gpus 1 --tensor-parallel-size 1 --text-encoder-tp-size 1 \
-  --usp 1 --ring 1 --vae-patch-parallel-size 1 \
-  --vae-parallel-mode tile --vae-use-tiling \
-  --quantization fp8 --enforce-eager \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-The 7200 s timeout used for T2VA is too short here: a 50-step Ref2VA request
-takes over an hour on this platform. Use 14400 s.
-
-Unlike `t2va`, `ref2va` defaults to a 16:9 output ratio, so `aspect_ratio` can be
-omitted when `width` and `height` are supplied.
-
-```bash
-curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
-  -D ref2va-headers.txt \
-  -w 'client_e2e_s=%{time_total}\n' \
-  --max-time 14400 \
-  -F 'input_reference=@/path/to/reference.jpg;type=image/jpeg' \
-  -F 'prompt=A hand rests on a wooden table in warm evening light, then slowly opens and turns toward the camera, with quiet room ambience.' \
-  -F 'width=960' \
-  -F 'height=576' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=50' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"ref2va","duration":8.0,"audio_flow_shift":3.0}' \
-  -o h3-gb10-ref2va.mp4
-```
-
-The response is `200 OK` with an MP4 body: H.264 at the requested geometry plus a
-32 kHz stereo AAC track. `ffprobe` reports 8.032 s for `duration=8.0`.
-
-## Measured latency
-
-Single GB10, FP8, eager, cuDNN attention, tiled VAE, one request at a time:
-
-| Workload | Steps | Text encode | Denoise | Per step | VAE decode | MP4 mux | Client E2E | Peak memory |
-| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
-| T2VA, 4 s, smoke shape | 10 | — | — | 8.68 s | — | 0.49 s | 95.9 s | — |
-| T2VA, 8 s, 960x576 | 50 | 0.25 s | 2088 s | 42.61 s | 70 s | 4.84 s | 2169.4 s (36 min 9 s) | 97.7 GiB |
-| Ref2VA, 8 s, 960x576, one image (3 runs) | 10 | 8.43-10.94 s | 665.5-748.8 s | 66.55-74.88 s | 67.9-69.8 s | 3.63 s | 770.3-861.1 s | 102.8 GiB |
-| Ref2VA, 8 s, 960x576, one image | 50 | 9.66 s | 4039.6 s | 80.79 s | 69.4 s | 3.63 s | 4157.0 s (69 min 17 s) | 102.8 GiB |
-
-How these were measured:
-
- Stage times come from `--enable-diffusion-pipeline-profiler`, read from the
-  `X-Stage-Durations` response header of `/v1/videos/sync`. The keys are
-  `MiniMaxH3Pipeline.encode_prompt` (text encode),
-  `MiniMaxH3Pipeline.diffuse` (denoise), and `MiniMaxH3Pipeline.decode`
-  (VAE decode).
- MP4 mux is not a header field. It is the
-  `Video response encoding (MP4 bytes)` line in the server log.
- Peak memory is the `X-Peak-Memory-MB` header, which reports the CUDA allocator
-  high-water mark (`torch.cuda.max_memory_reserved`) for the request. It excludes
-  the CUDA context and non-PyTorch allocations, so true pool usage is somewhat
-  higher. `nvidia-smi --query-gpu=memory.used` is not usable on GB10 — unified
-  memory has no discrete VRAM to report and the field returns `[N/A]`. See the
-  capacity section for a `/proc/meminfo` cross-check.
- For T2VA, text encode and VAE decode were measured on a separate 10-step run at
-  the same 960x576 / 8 s geometry. Both are independent of step count, so they
-  transfer to the 50-step row unchanged. The Ref2VA MP4 mux figure transfers the
-  same way, from the 10-step run at identical output geometry and duration.
- Ref2VA peak memory is byte-identical between the 10-step and 50-step runs
-  (`X-Peak-Memory-MB: 105318.000` in both), confirming that peak is set by output
-  geometry and reference input rather than step count.
- Stage times do not sum exactly to end-to-end. Queueing, result transfer, and
-  engine bookkeeping sit outside the profiled stages.
-
-Denoise dominates at 96% of end-to-end, so step count and geometry are the only
-knobs that materially change the wall clock on this platform.
-
-Ref2VA costs 1.92x the wall clock of T2VA at the same geometry and step count:
-4157.0 s versus 2169.4 s. Text encoding shows the most dramatic ratio — 9.66 s
-versus 0.25 s, 39x — but at 0.2% of end-to-end it is not what makes Ref2VA slow.
-The cost is in denoise. A single reference image expands the Qwen3-VL
-presentation to 6883 tokens (logged as `MiniMax H3 ref2va Qwen presentation:
-6883 tokens, 1 reference images`), and those tokens sit in the attention context
-of every denoise step. Per-step time rises from 42.61 s to 80.79 s, and that
-1.90x multiplies across all 50 steps. VAE decode is unchanged at ~69 s, as
-expected for an identical output shape.
-
-Repeated identical 10-step T2VA requests varied by up to 23% in denoise time
-(397 s to 490 s) on a machine that had already been under sustained load. Treat
-these as single-run measurements on one machine, not a throughput guarantee, and
-expect the slower end of that range for back-to-back jobs.
-
-Ref2VA per-step time is load-dependent in the same way. On an idle machine the
-first 10-step request ran at 66.55 s per step. The 50-step request that followed
-occupied the box for 69 consecutive minutes and averaged 80.79 s per step. Two
-further 10-step requests taken immediately afterwards settled at 74.88 s and
-74.31 s — 12.5% slower than the idle run, and within 0.8% of each other, so this
-is a stable thermal state rather than measurement noise.
-
-Plan for 81 s per step when sizing a full 50-step Ref2VA job; 66 s per step is
-only reachable on a cold machine and does not hold for the length of one request.
-
-Ref2VA text encode converged downward across the four runs (10.94 s, 9.66 s,
-8.52 s, 8.43 s) as first-touch costs fell away; treat ~8.5 s as steady state.
-VAE decode was stable at 67.9-69.8 s throughout.
-
-Set `VLLM_OMNI_VIDEO_SYNC_TIMEOUT` well above the expected request time — the
-default 1800 s is shorter than a 50-step run on this platform, and 7200 s is
-shorter than a 50-step Ref2VA run.
-
-## Known limitations
-
- One GPU means no Ulysses, ring, TP, or VAE patch parallelism. Pass
-  `--usp 1 --ring 1 --vae-patch-parallel-size 1` explicitly if a profile or
-  script would otherwise supply higher degrees.
- `--enforce-eager` is used because regional compile adds startup time without a
-  parallelism win on a single rank.
- `t2va` rejects requests without an explicit `aspect_ratio`. When `width` and
-  `height` are both supplied they take precedence and `aspect_ratio` only has to
-  name one of the supported ratios.
- Sustained load degrades throughput. See the variance notes above.
- Only one partition is resident. For Ref2VA, stop the FL2VA server and restart
-  with `/path/to/MiniMax-H3/Ref2VA`. Ref2VA with one reference image is measured
-  above; reference videos and additional images push the token count higher and
-  were not measured. With `MemAvailable` bottoming out at 7.4 GiB during a
-  single-image request, there is very little room to grow — re-measure before
-  adding references or raising the output shape.
- Ref2VA requires a vLLM-Omni build newer than `v0.26.0`. See the version note
-  under **Validated on**: FP8 weight loading and image-only Ref2VA are both
-  broken on `release/v0.26.0`.suggestion is  `v0.26.1`.
- Online FP8 is incompatible with layerwise offload — the offload path produces a
-  weight stride the Cutlass FP8 kernel rejects. This is not a practical
-  restriction here since offload is unusable on GB10 anyway.
-```
@@ -58,10 +58,6 @@ FlashAttention-4 extra:
 uv pip install -e '.[fa4]'
 ```

-On AMD ROCm, install without the `[fa4]` extra (FA4 is CUDA-only) and use
-`--diffusion-attention-backend FLASH_ATTN`; see
-[AMD ROCm (gfx942 / gfx950)](#amd-rocm-gfx942--gfx950).
-
 `ffmpeg` and `ffprobe` must be available on `PATH`. They are used for
 reference-video preparation and MP4 output.

@@ -391,101 +387,6 @@ incompatible with H3 layerwise offload because the offload path produces a
 weight stride rejected by the Cutlass FP8 kernel. Use resident FP8 with tensor
 parallelism and VAE tiling instead.

-## AMD ROCm (gfx942 / gfx950)
-
-The sections above describe the NVIDIA CUDA path. This section covers the AMD
-ROCm path; use it instead of the CUDA commands when running on AMD Instinct
-GPUs.
-
-MiniMax H3 runs on AMD Instinct GPUs (gfx942 / gfx950) in BF16. Use
-`--diffusion-attention-backend FLASH_ATTN`, which resolves to AITER packed varlen
-attention on both architectures.
-
-Select the device with `HIP_VISIBLE_DEVICES` (not `CUDA_VISIBLE_DEVICES`), drop the
-CUDA-only `FLASHINFER_DISABLE_VERSION_CHECK`, and install without the `[fa4]` extra
-(FA4 is CUDA-only). The VAE uses AITER GroupNorm on ROCm.
-
-Install (ROCm wheel + source vLLM-Omni):
-
-```bash
-pip install "vllm==0.26.0+rocm723" \
-  --extra-index-url https://wheels.vllm.ai/rocm/0.26.0/rocm723
-VLLM_OMNI_TARGET_DEVICE=rocm pip install -e . --no-build-isolation
-```
-
-Prebuilt image: `vllm/vllm-omni-rocm:minimax-h3`. All tasks work out of the box:
-the image bundles TorchCodec (for image+audio Ref2VA) and `ffmpeg` (for
-video-reference Ref2VA).
-
-### ROCm single GPU
-
-Single GPU with model-level CPU offload keeps the Qwen3-VL encoder and DiT from
-being co-resident:
-
-```bash
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8091
-
-HIP_VISIBLE_DEVICES=0 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni --host 0.0.0.0 --port "${PORT}" --trust-remote-code \
-  --num-gpus 1 --enable-cpu-offload \
-  --diffusion-attention-backend FLASH_ATTN
-```
-
-### ROCm four GPUs
-
-The best-practice CUDA four-GPU configuration works on ROCm with the changes above.
-It mirrors the CUDA command including Ulysses sequence parallelism, VAE patch
-parallelism, and text-encoder tensor parallelism, with no CPU offload when the model
-shards across the GPUs:
-
-```bash
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8091
-
-HIP_VISIBLE_DEVICES=0,1,2,3 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 4 \
-  --usp 4 \
-  --ring 1 \
-  --text-encoder-tp-size 4 \
-  --vae-patch-parallel-size 4 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend FLASH_ATTN
-```
-
-As on CUDA, H3 is CFG-distilled, so keep `--cfg-parallel-size` at 1, and the H3 VAE
-supports only its native `tile` mode. `--text-encoder-tp-size` is validated on
-gfx942; on gfx950 it was not exercised.
-
-### Validated ROCm evidence
-
-vLLM-Omni with MiniMax H3 support, BF16. gfx942 rows measured with the
-`vllm/vllm-omni-rocm:minimax-h3` image; gfx950 rows measured with the
-`0.26.0+rocm723` wheel (HIP 7.2).
-
-| Workload | Configuration | Observed result |
-|----------|---------------|-----------------|
-| T2VA, 1344x768, 209 frames, 50 steps | 4x gfx942 (MI300X), FLASH_ATTN, USP4, text-enc TP4, VAE PP4 tile | encode 0.09 s, denoise 244.04 s, decode 4.15 s, 267.42 s client E2E; H.264 24 FPS + 32 kHz stereo AAC |
-| FL2VA, 1344x768, 209 frames, 50 steps | 4x gfx942 (MI300X), FLASH_ATTN, USP4, text-enc TP4, VAE PP4 tile | encode 13.98 s, denoise 257.58 s, decode 4.11 s, 287.07 s client E2E; H.264 24 FPS + 32 kHz stereo AAC |
-| T2VA, 832x480, ~4 s, 40 steps | 1x gfx950 (MI350), FLASH_ATTN, CPU offload | valid MP4 (H.264 + synced audio); ~0.73 s/denoise-step (~1.37 it/s), ~55 s client E2E incl. warmup |
-
-gfx942 figures are the mean of three requests after one excluded warmup
-(external evidence: vllm-project/recipes#732). gfx950 figures are
-functional-correctness validations, not tuned throughput; the first request
-includes lazy regional compilation. MI325X (gfx942) and other MI355X SKUs are not
-listed until their own evidence is added.
-
 ## HTTP API examples

 The following requests use the synchronous endpoint so the returned body can
@@ -750,98 +651,19 @@ audio spectral cosine 0.9589 (minimum 0.80), and audio RMS ratio 0.9342. The
 resident per-GPU peak was 68.52 GiB for BF16 and 53.51 GiB for FP8, a 22%
 reduction.

-## TeaCache acceleration
-
-TeaCache reuses DiT block residuals across denoising steps when consecutive
-timestep embeddings are similar. MiniMax-H3 TeaCache is currently calibrated
-only for the FL2VA partition. In combined serving, FL2VA requests use TeaCache
-while Ref2VA requests run uncached; Ref2VA-only serving rejects TeaCache.
-
-TeaCache and Cache-DiT are mutually exclusive; pick one cache backend per server.
-
-The model-specific default and examples use `rel_l1_thresh=0.17`, which
-provided the best conservative speed/quality balance in the validated 107-frame
-T2VA workload. Lower values
-may produce few or no cache hits, while higher values can improve performance
-at the cost of output quality. Validate the threshold on representative
-prompts and generation settings before changing it.
-
-### Offline (Python API)
-
-Export the directory containing the `FL2VA` and `Ref2VA` subdirectories before
-running the Python example, for example `export MODEL_ROOT=/models/MiniMax-H3`.
-
-```python
-import os
-
-from vllm_omni import Omni
-from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-
-omni = Omni(
-    model=os.path.join(os.environ["MODEL_ROOT"], "FL2VA"),
-    cache_backend="tea_cache",
-    cache_config={"rel_l1_thresh": 0.17},
-    trust_remote_code=True,
-    enable_cpu_offload=True,
-)
-outputs = omni.generate(
-    "A quiet cinematic night scene with matching ambient sound.",
-    OmniDiffusionSamplingParams(
-        height=256,
-        width=448,
-        num_frames=29,
-        fps=24,
-        num_inference_steps=50,
-        seed=42,
-        extra_args={
-            "task": "t2va",
-            "duration": 4.0,
-            "aspect_ratio": "16:9",
-            "flow_shift": 12.0,
-            "audio_flow_shift": 3.0,
-        },
-    ),
-)
-```
-
-### Online serving
-
-```bash
-vllm serve "${MODEL_ROOT}/FL2VA" \
-  --omni \
-  --trust-remote-code \
-  --cache-backend tea_cache \
-  --cache-config '{"rel_l1_thresh":0.17}'
-```
-
 ## Known limitations

- TeaCache is calibrated for FL2VA only; Ref2VA requests run uncached.
 - Combined serving requires sibling `FL2VA` and `Ref2VA` directories, loads
  both task-specific DiTs, and loads shared components once from `FL2VA`.
 - H3 currently executes one generation request per diffusion batch.
 - The first regional-compile request is a warmup and should not be included in
  steady-state performance measurements.
- The serving path accepts fewer references than the model supports. H3 documents up
-  to 9 images, 3 video clips, and 3 audio clips (12 files) per Omni Reference
-  request; the current vLLM-Omni path takes exactly one image plus one audio
-  reference, or one or more videos with no separate `audio_reference` (it uses the
-  source soundtracks).
- The 768 px short-edge mode is available for T2VA and FL2VA; 1344x768 is the
-  documented 16:9 request shape.
- `--cfg-parallel-size > 1` is rejected by design (CFG-distilled, no negative branch).
- VAE patch parallelism requires size 1 or the full DiT group size and supports the
-  H3 native `tile` mode only.
- A U2 x Ring2 hybrid currently fails with an attention-mask length mismatch; use
-  pure Ulysses.
 - Online FP8 is not compatible with layerwise offload.
- TeaCache and Cache-DiT cannot be enabled on the same server.
 - Image+audio Ref2VA accepts exactly one image and one audio reference.
 - Video Ref2VA accepts one or more video files, but not an additional standalone
  audio reference.
- Pure Ulysses still replicates the full DiT on every rank, so smaller-memory GPUs
-  cannot use `--usp N --tp 1` as a resident capacity path. Use DiT tensor parallelism
-  or model-level CPU offload; text-encoder TP alone is not sufficient.
+- VAE patch parallelism requires size 1 or the full DiT group size and supports
+  the H3 native `tile` mode only.

 ## Additional resources

@@ -19,11 +19,6 @@ add files for this repo. Use one Markdown file per model family by default.
 > Individual pages resolve at `https://recipes.vllm.ai/<provider>/<model-id>`,
 > e.g. [`bosonai/higgs-audio-v3-tts-4b`](https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b).

-The `Recipe` column in the Supported Models documentation links to the
-published recipe when available and otherwise to the corresponding recipe in
-this directory. The recipe files remain the source of truth for commands and
-validation details.
-
 Example layout:

 ```text
@@ -1805,7 +1805,6 @@ class TestQwen2_5OmniPipeline:
        assert s.owns_tokenizer is True
        assert s.engine_output_type == "latent"
        assert s.requires_multimodal_data is True
-        assert s.hf_config_name == "thinker_config"

    def test_talker(self):
        p = resolve_pipeline_config("qwen2_5_omni")
@@ -1814,7 +1813,6 @@ class TestQwen2_5OmniPipeline:
        s = p.get_stage(1)
        assert isinstance(s, StagePipelineConfig)
        assert s.input_sources == (0,)
-        assert s.hf_config_name == "talker_config"
        assert s.sampling_constraints["stop_token_ids"] == [8294]
        # thinker2talker was removed: qwen2_5_omni has no async_chunk support,
        # so sync_process_input_func always wins and custom_process_input_func
@@ -1831,7 +1829,6 @@ class TestQwen2_5OmniPipeline:
        assert s.execution_type == StageExecutionType.LLM_GENERATION
        assert s.final_output_type == "audio"
        assert s.engine_output_type == "audio"
-        assert s.hf_config_name == "thinker_config"


 class TestQwen3TTSPipeline:
@@ -39,7 +39,6 @@ from vllm_omni.config.stage_config import (
    load_deploy_config,
    merge_pipeline_deploy,
 )
-from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
 from vllm_omni.engine.stage_init_utils import build_legacy_engine_args_dict

 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -967,24 +966,20 @@ def test_diffusion_config_from_kwargs_reuses_legacy_normalization(monkeypatch):

    cfg = omni_config_module._DiffusionConfigProjection.from_kwargs(
        diffusion_attention_backend="flash_attn",
-        fa_deterministic=True,
        kv_cache_dtype="fp8",
        kv_cache_skip_steps="0-1",
        kv_cache_skip_layers=[2],
        static_lora_scale=0.25,
-        diffusion_kv_mode="paged_scheduler",
        diffusers_load_kwargs=None,
        diffusers_call_kwargs=None,
    )

    assert cfg.diffusion_attention_config.default.backend == "flash_attn"
-    assert cfg.fa_deterministic is True
    assert cfg.diffusion_kv_cache_dtype == "fp8"
    assert cfg.diffusion_kv_cache_skip_step_indices == {0, 1}
    assert cfg.diffusion_kv_cache_skip_layer_indices == {2}
    assert cfg.lora_scale == 0.25
    assert cfg.cache_backend == "tea_cache"
-    assert cfg.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
    assert cfg.diffusers_load_kwargs == {}
    assert cfg.diffusers_call_kwargs == {}

@@ -999,8 +994,6 @@ def test_from_pipeline_config_normalizes_diffusion_config_aliases_from_engine_ar
                "stages:",
                "  - stage_id: 0",
                "    diffusion_attention_backend: flash_attn",
-                "    fa_deterministic: true",
-                "    diffusion_kv_mode: paged_scheduler",
            ]
        )
    )
@@ -1012,29 +1005,6 @@ def test_from_pipeline_config_normalizes_diffusion_config_aliases_from_engine_ar

    assert isinstance(stage, VllmOmniDiffusionStageConfig)
    assert stage.diffusion_config.diffusion_attention_config.default.backend == "flash_attn"
-    assert stage.diffusion_config.fa_deterministic is True
-    assert stage.diffusion_config.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
-
-
-def test_from_pipeline_config_rejects_reserved_diffusion_kv_mode(tmp_path):
-    deploy_path = tmp_path / "dreamzero_reserved_diffusion_kv.yaml"
-    deploy_path.write_text(
-        "\n".join(
-            [
-                "pipeline: dreamzero",
-                "async_chunk: false",
-                "stages:",
-                "  - stage_id: 0",
-                "    diffusion_kv_mode: paged_worker_local",
-            ]
-        )
-    )
-
-    with pytest.raises(ValueError, match="reserved but not implemented"):
-        _from_pipeline_key(
-            "dreamzero",
-            deploy_config_path=str(deploy_path),
-        )


 def test_diffusion_config_field_classification_covers_current_fields():
@@ -1055,7 +1025,6 @@ def test_diffusion_config_field_classification_covers_current_fields():
        "enable_session_state_manager",
        "prompt_embed_cache_size",
        "diffusion_kv_cache_dtype",
-        "diffusion_kv_mode",
    } <= omni_config_module._DIFFUSION_ONLY_CONFIG_FIELDS
    assert {
        "revision",
@@ -1,192 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Equivalence and session-isolation tests for Cosmos3StateAdapter (RFC #4480).
-
-These drive the adapter directly with tiny CPU tensors -- no model, no GPU --
-and assert it stores/returns the per-branch UND K/V exactly and isolates
-durable state between sessions. They do not cover the transformer's mutable
-load-to-forward handoff.
-"""
-
-from __future__ import annotations
-
-import pytest
-import torch
-
-from vllm_omni.experimental.world_models.adapters.state_cosmos3_adapter import (
-    Cosmos3StateAdapter,
-)
-from vllm_omni.experimental.world_models.session_state import SessionStateManager
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-
-LAYERS = 3
-SEQ, DIM = 3, 4
-
-
-def _fake_cached_kv(seed: int) -> list[tuple[torch.Tensor, torch.Tensor]]:
-    """A list of per-layer (K, V); contents seeded so branches/sessions differ."""
-    g = torch.Generator().manual_seed(seed)
-    return [(torch.randn(1, SEQ, DIM, generator=g), torch.randn(1, SEQ, DIM, generator=g)) for _ in range(LAYERS)]
-
-
-def _adapter(session_id: str, manager: SessionStateManager | None = None) -> Cosmos3StateAdapter:
-    # `manager is not None`, not `manager or ...`: an empty SessionStateManager is
-    # falsy (it defines __len__), so `or` would silently swap in a fresh manager.
-    return Cosmos3StateAdapter(session_id, manager if manager is not None else SessionStateManager())
-
-
-def _assert_kv_equal(got: list | None, expected: list) -> None:
-    assert got is not None and len(got) == len(expected) == LAYERS
-    for (k, v), (ke, ve) in zip(got, expected):
-        torch.testing.assert_close(k, ke)
-        torch.testing.assert_close(v, ve)
-
-
-class _FakeTransformer:
-    cached_kv = None
-    cached_freqs_gen = None
-
-
-# ----------------------------- equivalence -----------------------------
-
-
-def test_branch_starts_uninitialized() -> None:
-    a = _adapter("s0")
-    for is_neg in (False, True):
-        assert a.is_branch_initialized(is_neg) is False
-        assert a.get_branch_kv(is_neg) is None
-
-
-def test_set_then_get_roundtrip() -> None:
-    a = _adapter("s0")
-    kv = _fake_cached_kv(1)
-    a.set_branch_kv(False, kv)
-    assert a.is_branch_initialized(False) is True
-    _assert_kv_equal(a.get_branch_kv(False), kv)
-
-
-def test_cond_uncond_branches_isolated() -> None:
-    a = _adapter("s0")
-    kv_pos, kv_neg = _fake_cached_kv(1), _fake_cached_kv(2)
-    a.set_branch_kv(False, kv_pos)
-    a.set_branch_kv(True, kv_neg)
-    _assert_kv_equal(a.get_branch_kv(False), kv_pos)
-    _assert_kv_equal(a.get_branch_kv(True), kv_neg)
-
-
-def test_encode_once_capture_is_noop_when_initialized() -> None:
-    a = _adapter("s0")
-    kv = _fake_cached_kv(1)
-    a.set_branch_kv(False, kv)
-    tr = _FakeTransformer()
-    tr.cached_kv = _fake_cached_kv(999)  # different content
-    a.capture_from_transformer(tr, False)
-    _assert_kv_equal(a.get_branch_kv(False), kv)  # still the first one
-
-
-def test_capture_writes_when_uninitialized() -> None:
-    a = _adapter("s0")
-    tr = _FakeTransformer()
-    tr.cached_kv = _fake_cached_kv(5)
-    tr.cached_freqs_gen = (torch.ones(2), torch.zeros(2))
-    a.capture_from_transformer(tr, False)
-    _assert_kv_equal(a.get_branch_kv(False), _fake_cached_kv(5))
-
-
-def test_capture_without_freqs_does_not_partially_initialize() -> None:
-    a = _adapter("s0")
-    tr = _FakeTransformer()
-    tr.cached_kv = _fake_cached_kv(5)
-    tr.cached_freqs_gen = None
-    with pytest.raises(RuntimeError, match="did not produce GEN RoPE frequencies"):
-        a.capture_from_transformer(tr, False)
-    assert a.is_branch_initialized(False) is False
-
-
-def test_load_into_transformer_without_freqs_sets_kv() -> None:
-    a = _adapter("s0")
-    kv = _fake_cached_kv(1)
-    a.set_branch_kv(False, kv)
-    tr = _FakeTransformer()
-    a.load_into_transformer(tr, False)
-    _assert_kv_equal(tr.cached_kv, kv)
-    assert tr.cached_freqs_gen is None
-
-
-def test_set_then_get_preserves_per_layer_values() -> None:
-    # The stored value must reflect the tensors passed in (per-layer).
-    a = _adapter("s0")
-    kv = _fake_cached_kv(3)
-    a.set_branch_kv(False, kv)
-    _assert_kv_equal(a.get_branch_kv(False), kv)
-
-
-def test_load_into_transformer_restores_kv_and_freqs_gen() -> None:
-    a = _adapter("s0")
-    tr = _FakeTransformer()
-    tr.cached_kv = _fake_cached_kv(3)
-    tr.cached_freqs_gen = (torch.ones(2), torch.zeros(2))
-    a.capture_from_transformer(tr, False)
-    tr.cached_kv = None
-    tr.cached_freqs_gen = None
-    a.load_into_transformer(tr, False)
-    _assert_kv_equal(tr.cached_kv, _fake_cached_kv(3))
-    assert tr.cached_freqs_gen is not None
-    torch.testing.assert_close(tr.cached_freqs_gen[0], torch.ones(2))
-
-
-def test_partial_branch_raises() -> None:
-    a = _adapter("s0")
-    a.set_branch_kv(False, _fake_cached_kv(1))
-    a._session.get("und_kv/1").reset()  # type: ignore[union-attr]
-    with pytest.raises(RuntimeError, match="partially initialized"):
-        a.get_branch_kv(False)
-
-
-# ----------------------------- reset -----------------------------
-
-
-def test_reset_clears_both_branches() -> None:
-    a = _adapter("s0")
-    a.set_branch_kv(False, _fake_cached_kv(1))
-    a.set_branch_kv(True, _fake_cached_kv(2))
-    a.reset()
-    for is_neg in (False, True):
-        assert a.is_branch_initialized(is_neg) is False
-        assert a.get_branch_kv(is_neg) is None
-
-
-# ----------------------- concurrency isolation (core) -----------------------
-
-
-def test_two_sessions_do_not_clobber() -> None:
-    manager = SessionStateManager()
-    a, b = _adapter("A", manager), _adapter("B", manager)
-    kv_a, kv_b = _fake_cached_kv(10), _fake_cached_kv(20)
-    a.set_branch_kv(False, kv_a)
-    assert b.is_branch_initialized(False) is False  # B not seeing A's state
-    b.set_branch_kv(False, kv_b)
-    _assert_kv_equal(a.get_branch_kv(False), kv_a)
-    _assert_kv_equal(b.get_branch_kv(False), kv_b)
-
-
-def test_fresh_adapter_same_session_sees_prior_state() -> None:
-    manager = SessionStateManager()
-    kv = _fake_cached_kv(7)
-    _adapter("s", manager).set_branch_kv(False, kv)
-    again = Cosmos3StateAdapter("s", manager)
-    _assert_kv_equal(again.get_branch_kv(False), kv)
-
-
-def test_adapter_survives_session_lru_eviction() -> None:
-    # An in-use adapter keeps its state even after the manager evicts its
-    # session id from the lookup table (LRU bounded by max_sessions).
-    manager = SessionStateManager(max_sessions=2)
-    a = _adapter("active", manager)
-    kv = _fake_cached_kv(11)
-    a.set_branch_kv(False, kv)
-    for i in range(3):
-        _adapter(f"other{i}", manager)
-    assert "active" not in manager
-    _assert_kv_equal(a.get_branch_kv(False), kv)
@@ -43,9 +43,9 @@
        ],
        "baseline": {
          "H100": {
-            "throughput_qps": 0.0361,
-            "latency_mean": 27.6206,
-            "peak_memory_mb_mean": 80548.0
+            "throughput_qps": 0.0434,
+            "latency_mean": 23.0654,
+            "peak_memory_mb_mean": 76360.0
          }
        }
      }
@@ -100,9 +100,9 @@
        ],
        "baseline": {
          "H100": {
-            "throughput_qps": 0.05263,
-            "latency_mean": 18.9415,
-            "peak_memory_mb_mean": 50053.7
+            "throughput_qps": 0.0606,
+            "latency_mean": 16.4928,
+            "peak_memory_mb_mean": 47164.8
          }
        }
      },
@@ -127,9 +127,9 @@
        ],
        "baseline": {
          "H100": {
-            "throughput_qps": 0.009595,
-            "latency_mean": 104.1058,
-            "peak_memory_mb_mean": 59718.0
+            "throughput_qps": 0.0124,
+            "latency_mean": 80.7784,
+            "peak_memory_mb_mean": 55374.3429
          }
        }
      }
@@ -471,66 +471,6 @@ class TestTeaCacheBackend:
        assert backend.enabled is True
        mock_apply_hook.assert_called_once()

-    @patch("vllm_omni.diffusion.cache.teacache.backend.apply_teacache_hook")
-    def test_enable_uses_generic_default_threshold(self, mock_apply_hook):
-        pipeline = Mock()
-        pipeline.__class__.__name__ = "QwenImagePipeline"
-        pipeline.transformer = Mock()
-        pipeline.transformer.__class__.__name__ = "QwenImageTransformer2DModel"
-
-        TeaCacheBackend(DiffusionCacheConfig()).enable(pipeline)
-        assert mock_apply_hook.call_args.args[1].rel_l1_thresh == 0.2
-
-    @pytest.mark.parametrize("partition", ["fl2va", "combined"])
-    @pytest.mark.parametrize(
-        ("configured_threshold", "expected_threshold"),
-        [(None, 0.17), (0.2, 0.2)],
-    )
-    @patch("vllm_omni.diffusion.cache.teacache.backend.apply_teacache_hook")
-    def test_minimax_h3_only_enables_fl2va_teacache(
-        self,
-        mock_apply_hook,
-        partition,
-        configured_threshold,
-        expected_threshold,
-    ):
-        pipeline = Mock()
-        pipeline.__class__.__name__ = "MiniMaxH3Pipeline"
-        pipeline.partition = partition
-        pipeline.transformer = Mock()
-        pipeline.transformer.__class__.__name__ = "MiniMaxH3DiTModel"
-        pipeline.transformers_ref = Mock()
-
-        config = (
-            DiffusionCacheConfig()
-            if configured_threshold is None
-            else DiffusionCacheConfig(rel_l1_thresh=configured_threshold)
-        )
-        backend = TeaCacheBackend(config)
-        backend.enable(pipeline)
-
-        mock_apply_hook.assert_called_once()
-        transformer, teacache_config = mock_apply_hook.call_args.args
-        assert transformer is pipeline.transformer
-        assert transformer is not pipeline.transformers_ref
-        assert teacache_config.rel_l1_thresh == expected_threshold
-
-    @patch("vllm_omni.diffusion.cache.teacache.backend.apply_teacache_hook")
-    def test_minimax_h3_rejects_ref2va_teacache(self, mock_apply_hook):
-        pipeline = Mock()
-        pipeline.__class__.__name__ = "MiniMaxH3Pipeline"
-        pipeline.partition = "ref2va"
-        pipeline.transformer = Mock()
-        pipeline.transformer.__class__.__name__ = "MiniMaxH3DiTModel"
-
-        backend = TeaCacheBackend(DiffusionCacheConfig())
-
-        with pytest.raises(ValueError, match="only supports the MiniMax-H3 FL2VA partition"):
-            backend.enable(pipeline)
-
-        assert backend.enabled is False
-        mock_apply_hook.assert_not_called()
-
    @patch("vllm_omni.diffusion.cache.teacache.backend.apply_teacache_hook")
    def test_enable_with_coefficients(self, mock_apply_hook):
        """Test enabling TeaCache with custom coefficients."""
@@ -15,23 +15,19 @@ Currently implemented:
 - TestFlux2KleinExtractor: Flux2Klein model extractor
 - TestFlux2Extractor: Flux2 model extractor
 - TestFluxExtractor: Flux model extractor
- TestMiniMaxH3Extractor: MiniMaxH3DiTModel extractor
 """

 from abc import ABC, abstractmethod
-from types import SimpleNamespace
 from unittest.mock import MagicMock, Mock, patch

 import pytest
 import torch
-import torch.nn as nn

 from tests.helpers.mark import hardware_test
 from vllm_omni.diffusion.cache.teacache.extractors import (
    extract_flux2_context,
    extract_flux2_klein_context,
    extract_flux_context,
-    extract_minimax_h3_context,
 )
 from vllm_omni.diffusion.models.flux.flux_transformer import FluxTransformer2DModel
 from vllm_omni.diffusion.models.flux2_klein.flux2_klein_transformer import (
@@ -427,280 +423,3 @@ class TestFluxExtractor(BaseExtractorTest):
                img_ids=torch.randint(0, 64, (1, 16, 3)),
                txt_ids=torch.randint(0, 64, (1, 8, 3)),
            )
-
-
-class _MiniMaxH3FakeLinear(nn.Module):
-    def __init__(
-        self,
-        in_features,
-        out_features,
-        *,
-        bias=False,
-        params_dtype=None,
-        quant_config=None,
-        prefix="",
-        total_num_heads=None,
-        total_num_kv_heads=None,
-        **kwargs,
-    ):
-        del kwargs
-        super().__init__()
-        self.prefix = prefix
-        self.quant_config = quant_config
-        self.weight = nn.Parameter(torch.randn(out_features, in_features, dtype=params_dtype or torch.float32))
-        if bias:
-            self.bias = nn.Parameter(torch.zeros(out_features, dtype=params_dtype or torch.float32))
-        else:
-            self.register_parameter("bias", None)
-        self.num_heads = total_num_heads
-        self.num_kv_heads = total_num_kv_heads
-
-    def forward(self, x):
-        return torch.nn.functional.linear(x, self.weight, self.bias), None
-
-
-class _MiniMaxH3FakeMergedLinear(_MiniMaxH3FakeLinear):
-    def __init__(self, in_features, out_features, **kwargs):
-        super().__init__(in_features, sum(out_features), **kwargs)
-
-
-class _MiniMaxH3FakeQKVLinear(_MiniMaxH3FakeLinear):
-    def __init__(
-        self,
-        *,
-        hidden_size,
-        head_size,
-        total_num_heads,
-        total_num_kv_heads,
-        **kwargs,
-    ):
-        qkv_features = (total_num_heads + 2 * total_num_kv_heads) * head_size
-        super().__init__(
-            hidden_size,
-            qkv_features,
-            total_num_heads=total_num_heads,
-            total_num_kv_heads=total_num_kv_heads,
-            **kwargs,
-        )
-
-
-class _MiniMaxH3FakeAttention(nn.Module):
-    class FakeBackend:
-        supports_prefix_kv_slicing = False
-
-    def __init__(self, **kwargs):
-        del kwargs
-        super().__init__()
-        self.attn_backend = self.FakeBackend
-        self.use_ring = False
-
-    def forward(self, q, k, v, metadata=None):
-        del k, v, metadata
-        return q
-
-
-def _minimax_h3_small_od_config():
-    arch = {
-        "num_layers": 1,
-        "token_refiner_num_layers": 1,
-        "hidden_size": 8,
-        "num_attention_heads": 1,
-        "attention_head_dim": 8,
-        "ffn_hidden_size": 16,
-        "latents_dim": 2,
-        "audio_latents_dim": 2,
-        "patch_size": (1, 2, 2),
-        "text_dim": 6,
-        "timestep_input_dim": 4,
-        "time_embed_hidden_size": 8,
-        "time_embed_dim": 4,
-        "adaln_out_features": 18 * 8,
-        "final_adaln_out_features": 2 * 8,
-        "rope_inv_freq_len": 1,
-    }
-    return SimpleNamespace(
-        tf_model_config=arch,
-        parallel_config=SimpleNamespace(ulysses_degree=1),
-    )
-
-
-def _minimax_h3_sample_kwargs(*, seq_len: int = 8, device: torch.device | str = "cpu") -> dict:
-    video_row_dim = 2 * 1 * 2 * 2
-    audio_row_dim = 2
-    text_len = 2
-    img_rows = 2
-
-    img_pos = torch.tensor([2, 3], dtype=torch.long, device=device)
-    audio_pos = torch.tensor([4, 5], dtype=torch.long, device=device)
-    text_pos = torch.tensor([0, 1], dtype=torch.long, device=device)
-    infer_out_pos = img_pos.clone()
-
-    token_tags = torch.full((seq_len,), -1, dtype=torch.long, device=device)
-    token_tags[text_pos] = 1
-    token_tags[img_pos] = 0
-    token_tags[audio_pos] = 2
-
-    inverse_indices = torch.zeros(seq_len, dtype=torch.long, device=device)
-
-    return {
-        "x": torch.randn(1, seq_len, video_row_dim, device=device),
-        "audio_x": torch.randn(1, seq_len, audio_row_dim, device=device),
-        "img_position_ids": torch.zeros(1, seq_len, 3, dtype=torch.float64, device=device),
-        "unique_timesteps": torch.tensor([0.5], dtype=torch.float32, device=device),
-        "inverse_indices": inverse_indices,
-        "update_mask": torch.ones(img_rows, dtype=torch.bool, device=device),
-        "token_tags": token_tags,
-        "prompt_embeds": torch.randn(text_len, 6, device=device),
-        "img_pos_info": {"position_ids": img_pos},
-        "audio_pos_info": {"position_ids": audio_pos},
-        "text_pos_info": {"position_ids": text_pos},
-        "img_pos_for_infer_output_info": {"position_ids": infer_out_pos},
-        "packed_seq_params": {
-            "cu_seqlens_q": torch.tensor([0, seq_len], dtype=torch.int32, device=device),
-            "max_seqlen_q": seq_len,
-        },
-        "refiner_packed_seq_params": {
-            "cu_seqlens_q": torch.tensor([0, text_len], dtype=torch.int32, device=device),
-            "max_seqlen_q": text_len,
-        },
-    }
-
-
-@pytest.mark.cpu
-class TestMiniMaxH3Extractor(BaseExtractorTest):
-    """Test extract_minimax_h3_context function."""
-
-    def get_extractor(self):
-        return extract_minimax_h3_context
-
-    @pytest.fixture
-    def minimax_h3_module(self, monkeypatch):
-        """Create a minimal MiniMaxH3DiTModel with fake parallel linears for CPU tests."""
-        from vllm_omni.diffusion.models.minimax_h3 import minimax_h3_transformer as h3
-
-        monkeypatch.setattr(h3, "ColumnParallelLinear", _MiniMaxH3FakeLinear)
-        monkeypatch.setattr(h3, "MergedColumnParallelLinear", _MiniMaxH3FakeMergedLinear)
-        monkeypatch.setattr(h3, "QKVParallelLinear", _MiniMaxH3FakeQKVLinear)
-        monkeypatch.setattr(h3, "RowParallelLinear", _MiniMaxH3FakeLinear)
-        monkeypatch.setattr(h3, "Attention", _MiniMaxH3FakeAttention)
-        monkeypatch.setattr(h3, "get_tensor_model_parallel_world_size", lambda: 1)
-
-        model = h3.MiniMaxH3DiTModel(_minimax_h3_small_od_config(), quant_config=None)
-        for submodule in model.modules():
-            if isinstance(submodule, h3.MiniMaxH3Attention):
-                submodule.rope._forward_method = submodule.rope.forward_native
-        model.eval()
-        return model
-
-    def get_module(self, minimax_h3_module):
-        return minimax_h3_module
-
-    @pytest.fixture
-    def sample_inputs(self):
-        """Create sample packed forward kwargs for MiniMaxH3DiTModel."""
-        return _minimax_h3_sample_kwargs(seq_len=8)
-
-    def get_sample_inputs(self, sample_inputs):
-        return sample_inputs
-
-    def test_modulated_input_shape(self, minimax_h3_module, sample_inputs):
-        """Test that modulated_input matches packed sequence shape [T, H]."""
-        context = extract_minimax_h3_context(minimax_h3_module, **sample_inputs)
-
-        seq_len = sample_inputs["x"].shape[1]
-        assert context.modulated_input.shape == (seq_len, minimax_h3_module.hidden_size)
-
-    def test_run_transformer_blocks_callable(self, minimax_h3_module, sample_inputs):
-        """Test that run_transformer_blocks is callable."""
-        context = extract_minimax_h3_context(minimax_h3_module, **sample_inputs)
-        assert callable(context.run_transformer_blocks)
-
-    def test_postprocess_callable(self, minimax_h3_module, sample_inputs):
-        """Test that postprocess is callable."""
-        context = extract_minimax_h3_context(minimax_h3_module, **sample_inputs)
-        assert callable(context.postprocess)
-
-    def test_postprocess_output_shape(self, minimax_h3_module, sample_inputs):
-        """Test that postprocess returns video/audio logits for infer rows."""
-        context = extract_minimax_h3_context(minimax_h3_module, **sample_inputs)
-        (hidden,) = context.run_transformer_blocks()
-        video_logits, audio_logits = context.postprocess(hidden)
-
-        num_video_rows = sample_inputs["img_pos_info"]["position_ids"].shape[0]
-        num_audio_rows = sample_inputs["audio_pos_info"]["position_ids"].shape[0]
-        assert video_logits.shape[0] == num_video_rows
-        assert audio_logits.shape[0] == num_audio_rows
-
-    def test_extractor_matches_native_forward(self, minimax_h3_module, sample_inputs):
-        """The uncached extractor path must preserve the model's forward result."""
-        expected_video, expected_audio = minimax_h3_module(**sample_inputs)
-
-        context = extract_minimax_h3_context(minimax_h3_module, **sample_inputs)
-        (hidden,) = context.run_transformer_blocks()
-        actual_video, actual_audio = context.postprocess(hidden)
-
-        torch.testing.assert_close(actual_video, expected_video)
-        torch.testing.assert_close(actual_audio, expected_audio)
-
-    def test_run_transformer_blocks_forwards_packed_layout(
-        self,
-        minimax_h3_module,
-        sample_inputs,
-        monkeypatch,
-    ):
-        """The extractor block call must mirror the native packed contract."""
-        from vllm_omni.diffusion.attention.backends.abstract import VideoTokenLayout
-
-        video_layout = VideoTokenLayout(prefix_len=2, latent_grid=(1, 1, 2))
-        inputs = {**sample_inputs, "video_token_layout": video_layout}
-        block = minimax_h3_module.blocks[0]
-        original_forward = block.forward
-        received: list[tuple[int, VideoTokenLayout | None]] = []
-
-        def capture_forward(*args, **kwargs):
-            received.append((kwargs["packed_total"], kwargs["video_layout"]))
-            return original_forward(*args, **kwargs)
-
-        monkeypatch.setattr(block, "forward", capture_forward)
-        context = extract_minimax_h3_context(minimax_h3_module, **inputs)
-        context.run_transformer_blocks()
-
-        assert received == [(sample_inputs["x"].shape[1], video_layout)]
-
-    def test_teacache_reuses_h3_block_residual(self, minimax_h3_module, sample_inputs, monkeypatch):
-        """A guaranteed cache hit must skip the H3 transformer block."""
-        from vllm_omni.diffusion.cache.teacache.config import TeaCacheConfig
-        from vllm_omni.diffusion.cache.teacache.hook import TeaCacheHook
-
-        block = minimax_h3_module.blocks[0]
-        original_forward = block.forward
-        block_calls = 0
-
-        def counted_forward(*args, **kwargs):
-            nonlocal block_calls
-            block_calls += 1
-            return original_forward(*args, **kwargs)
-
-        monkeypatch.setattr(block, "forward", counted_forward)
-        hook = TeaCacheHook(
-            TeaCacheConfig(
-                transformer_type="MiniMaxH3DiTModel",
-                rel_l1_thresh=0.3,
-            )
-        )
-        hook.initialize_hook(minimax_h3_module)
-
-        hook.new_forward(minimax_h3_module, **sample_inputs)
-        video_logits, audio_logits = hook.new_forward(minimax_h3_module, **sample_inputs)
-
-        assert block_calls == 1
-        assert video_logits.shape[0] == sample_inputs["img_pos_info"]["position_ids"].shape[0]
-        assert audio_logits.shape[0] == sample_inputs["audio_pos_info"]["position_ids"].shape[0]
-
-    def test_invalid_module_raises_error(self):
-        """Test that invalid module without blocks raises ValueError."""
-        invalid_module = Mock()
-        invalid_module.blocks = []
-
-        with pytest.raises(ValueError, match="Module must have blocks"):
-            extract_minimax_h3_context(invalid_module, **_minimax_h3_sample_kwargs())
@@ -1,52 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import pytest
-
-from vllm_omni.diffusion.data import OmniDiffusionConfig
-from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
-
-
-@pytest.fixture(autouse=True)
-def _fixed_master_port(monkeypatch) -> None:
-    monkeypatch.setattr(OmniDiffusionConfig, "_resolve_master_port", lambda _self: 29500)
-
-
-def test_dense_legacy_is_default() -> None:
-    config = OmniDiffusionConfig.from_kwargs()
-
-    assert config.diffusion_kv_mode is DiffusionKVCacheMode.DENSE_LEGACY
-
-
-def test_paged_worker_local_is_rejected_until_implemented() -> None:
-    with pytest.raises(ValueError, match="reserved but not implemented"):
-        OmniDiffusionConfig.from_kwargs(diffusion_kv_mode="paged_worker_local")
-
-
-def test_unknown_cache_mode_is_rejected() -> None:
-    with pytest.raises(ValueError, match="Unsupported Diffusion KV diffusion_kv_mode"):
-        OmniDiffusionConfig.from_kwargs(diffusion_kv_mode="unknown")
-
-
-def test_non_mapping_omni_kv_config_is_rejected() -> None:
-    with pytest.raises(TypeError, match="omni_kv_config must be a mapping"):
-        OmniDiffusionConfig.from_kwargs(omni_kv_config="paged_scheduler")
-
-
-def test_paged_scheduler_rejects_dense_legacy_kv_receive() -> None:
-    with pytest.raises(ValueError, match="does not support imported AR KV"):
-        OmniDiffusionConfig.from_kwargs(
-            diffusion_kv_mode="paged_scheduler",
-            omni_kv_config={"need_recv_cache": True},
-        )
-
-
-def test_paged_scheduler_does_not_depend_on_model_registry() -> None:
-    config = OmniDiffusionConfig.from_kwargs(
-        model_class_name="FutureDiffusionModel",
-        diffusion_kv_mode="paged_scheduler",
-    )
-
-    assert config.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
@@ -1,200 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import pytest
-import torch
-import vllm.v1.core.single_type_kv_cache_manager as native_kv_managers
-from vllm.v1.core.kv_cache_manager import KVCacheManager
-from vllm.v1.core.kv_cache_utils import BlockHash
-from vllm.v1.kv_cache_interface import (
-    FullAttentionSpec,
-    KVCacheConfig,
-    KVCacheGroupSpec,
-    KVCacheTensor,
-)
-from vllm.v1.request import RequestStatus
-
-from vllm_omni.diffusion.diffusion_kv.request import DiffusionKVContext, DiffusionKVRequest
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
-
-BLOCK_SIZE = 4
-
-
-def _request(**overrides) -> DiffusionKVRequest:
-    values = dict(
-        request_id="req/diffusion-kv/0",
-        sequence_id=0,
-        prefix_len=4,
-        target_len=4,
-        seq_len=8,
-    )
-    values.update(overrides)
-    return DiffusionKVRequest(**values)
-
-
-def test_request_exposes_native_request_and_diffusion_semantics() -> None:
-    request = _request()
-
-    assert request.sequence_id == 0
-    assert request.prefix_len == 4
-    assert request.target_len == 4
-    assert request.num_tokens == request.seq_len == 8
-    assert request.num_prompt_tokens == 4
-    assert request.num_computed_tokens == 0
-    assert request.block_hashes == []
-    assert request.kv_contexts == ()
-    assert request.skip_reading_prefix_cache is True
-    assert request.shared_prefix_boundary == 0
-    assert request.status is RequestStatus.WAITING
-
-
-@pytest.mark.parametrize(
-    ("overrides", "message"),
-    [
-        ({"sequence_id": -1}, "sequence_id"),
-        ({"prefix_len": -1}, "prefix_len"),
-        ({"target_len": 0}, "target_len"),
-        ({"seq_len": 0}, "seq_len"),
-        ({"prefix_len": 5, "target_len": 4, "seq_len": 8}, "must not exceed"),
-    ],
-)
-def test_request_rejects_invalid_lengths(overrides, message: str) -> None:
-    with pytest.raises(ValueError, match=message):
-        _request(**overrides)
-
-
-@pytest.mark.parametrize(
-    ("overrides", "message"),
-    [
-        ({"context_id": ""}, "context_id"),
-        ({"cache_role": ""}, "cache_role"),
-        ({"num_tokens": 0}, "num_tokens"),
-    ],
-)
-def test_context_rejects_invalid_identity_or_length(overrides, message: str) -> None:
-    values = dict(context_id="text", cache_role="cross.text", num_tokens=8)
-    values.update(overrides)
-
-    with pytest.raises(ValueError, match=message):
-        DiffusionKVContext(**values)
-
-
-def test_request_owns_independent_kv_contexts() -> None:
-    text = DiffusionKVContext(context_id="text", cache_role="cross.text", num_tokens=8)
-    image = DiffusionKVContext(context_id="image", cache_role="cross.image", num_tokens=4)
-
-    request = _request(kv_contexts=(text, image))
-
-    assert request.kv_contexts == (text, image)
-
-
-def test_request_rejects_duplicate_context_ids() -> None:
-    contexts = (
-        DiffusionKVContext(context_id="condition", cache_role="cross.text", num_tokens=8),
-        DiffusionKVContext(context_id="condition", cache_role="cross.image", num_tokens=4),
-    )
-
-    with pytest.raises(ValueError, match="unique context_id"):
-        _request(kv_contexts=contexts)
-
-
-def test_request_rejects_non_context_values() -> None:
-    with pytest.raises(TypeError, match="DiffusionKVContext"):
-        _request(kv_contexts=(object(),))
-
-
-def _manager(*, enable_caching: bool) -> KVCacheManager:
-    # vLLM 0.26 lazily registers its built-in KV specs. Another test may have
-    # already registered an out-of-tree spec, making the registry non-empty
-    # before FullAttentionSpec is registered. Initialize the native mappings
-    # explicitly; vLLM 0.25 has no registration hook and needs no setup.
-    register_all = getattr(native_kv_managers, "register_all_kvcache_specs", None)
-    if register_all is not None:
-        register_all(None)
-
-    spec = FullAttentionSpec(
-        block_size=BLOCK_SIZE,
-        num_kv_heads=2,
-        head_size=8,
-        dtype=torch.bfloat16,
-    )
-    group = KVCacheGroupSpec(layer_names=["layer0"], kv_cache_spec=spec)
-    config = KVCacheConfig(
-        num_blocks=8,
-        kv_cache_tensors=[KVCacheTensor(size=spec.page_size_bytes * 8, shared_by=["layer0"])],
-        kv_cache_groups=[group],
-    )
-    return KVCacheManager(
-        config,
-        max_model_len=64,
-        scheduler_block_size=BLOCK_SIZE,
-        hash_block_size=BLOCK_SIZE,
-        enable_caching=enable_caching,
-    )
-
-
-def test_empty_hash_request_conforms_to_native_request_local_allocation() -> None:
-    manager = _manager(enable_caching=True)
-    free_before = manager.block_pool.get_num_free_blocks()
-    request = _request()
-
-    # vLLM 0.26 adds a shared-prefix-boundary return value.
-    computed_blocks, num_computed_tokens, *_ = manager.get_computed_blocks(request)
-    assert num_computed_tokens == 0
-    blocks = manager.allocate_slots(
-        request,
-        num_new_tokens=request.num_tokens,
-        new_computed_blocks=computed_blocks,
-        delay_cache_blocks=True,
-        full_sequence_must_fit=True,
-    )
-
-    assert blocks is not None
-    assert len(manager.get_block_ids(request.request_id)[0]) == 2
-    # Empty hashes intentionally mean request-local residency only. Calling
-    # native cache_blocks() would require a canonical hash for the full prefix
-    # block and is therefore outside this request's contract.
-    manager.free(request)
-    assert manager.block_pool.get_num_free_blocks() == free_before
-
-
-def test_hashed_request_conforms_to_native_delayed_prefix_commit() -> None:
-    manager = _manager(enable_caching=True)
-    prefix_hash = BlockHash(b"prefix".ljust(32, b"\0"))
-    target_hash = BlockHash(b"target".ljust(32, b"\0"))
-    request = _request(block_hashes=[prefix_hash, target_hash])
-
-    computed_blocks, num_computed_tokens, *_ = manager.get_computed_blocks(request)
-    assert num_computed_tokens == 0
-    blocks = manager.allocate_slots(
-        request,
-        num_new_tokens=request.num_tokens,
-        new_computed_blocks=computed_blocks,
-        delay_cache_blocks=True,
-        full_sequence_must_fit=True,
-    )
-
-    assert blocks is not None
-    manager.cache_blocks(request, request.prefix_len)
-    manager.free(request)
-
-    cached_request = _request(
-        request_id="req/diffusion-kv/cached",
-        block_hashes=[prefix_hash, target_hash],
-    )
-    cached_blocks, num_computed_tokens, *_ = manager.get_computed_blocks(cached_request)
-
-    # Only the stable prefix was published. The dynamic target remains a miss.
-    assert num_computed_tokens == cached_request.prefix_len
-    assert len(cached_blocks.blocks[0]) == 1
-    cached_allocation = manager.allocate_slots(
-        cached_request,
-        num_new_tokens=cached_request.num_tokens - num_computed_tokens,
-        num_new_computed_tokens=num_computed_tokens,
-        new_computed_blocks=cached_blocks,
-        delay_cache_blocks=True,
-        full_sequence_must_fit=True,
-    )
-    assert cached_allocation is not None
-    manager.free(cached_request)
@@ -244,7 +244,7 @@ def test_mindie_full_dim_rope_keeps_h3_cos_sin_layout(monkeypatch: pytest.Monkey
    captured: dict[str, object] = {}

    def rotary_position_embedding(x, cos, sin, **kwargs):
-        captured.update(cos=cos, sin=sin, kwargs=kwargs)
+        captured.update(x=x, cos=cos, sin=sin, kwargs=kwargs)
        return x

    monkeypatch.setitem(
@@ -256,8 +256,10 @@ def test_mindie_full_dim_rope_keeps_h3_cos_sin_layout(monkeypatch: pytest.Monkey
    cos = torch.randn(11, 96, dtype=torch.bfloat16)
    sin = torch.randn(11, 96, dtype=torch.bfloat16)

-    apply_rotary_emb_mindiesd(x, cos, sin, interleaved=False, half_head_dim=False)
+    actual = apply_rotary_emb_mindiesd(x, cos, sin, interleaved=False, half_head_dim=False)

+    assert actual is x
+    assert captured["x"] is x
    assert captured["cos"] is cos
    assert captured["sin"] is sin
    assert captured["kwargs"] == {
@@ -265,31 +267,3 @@ def test_mindie_full_dim_rope_keeps_h3_cos_sin_layout(monkeypatch: pytest.Monkey
        "head_first": False,
        "fused": True,
    }
-
-
-def test_mindie_rope_restores_3d_layout(monkeypatch: pytest.MonkeyPatch) -> None:
-    """mindiesd rotary_position_embedding only accepts 4D ``x``."""
-    captured: dict[str, torch.Tensor] = {}
-
-    def rotary_position_embedding(x, cos, sin, **kwargs):
-        # Mirror mindiesd's own input guard.
-        assert x.dim() == 4, f"mindiesd requires 4D x, got {x.dim()}"
-        captured.update(x=x)
-        return x
-
-    monkeypatch.setitem(
-        sys.modules,
-        "mindiesd",
-        types.SimpleNamespace(rotary_position_embedding=rotary_position_embedding),
-    )
-
-    S, H, D = 11, 3, 96
-    x = torch.randn(S, H, D, dtype=torch.bfloat16)
-    cos = torch.randn(S, D, dtype=torch.bfloat16)
-    sin = torch.randn(S, D, dtype=torch.bfloat16)
-
-    actual = apply_rotary_emb_mindiesd(x, cos, sin, interleaved=False, half_head_dim=False)
-
-    assert captured["x"].shape == (1, S, H, D)
-    assert actual.shape == (S, H, D)
-    torch.testing.assert_close(actual, x, atol=0, rtol=0)
@@ -16,7 +16,6 @@ from PIL import Image
 from torch import nn

 from vllm_omni.diffusion.worker.request_batch import DiffusionRequestBatch
-from vllm_omni.experimental.world_models.session_state import SessionStateManager

 pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]

@@ -426,29 +425,6 @@ def test_distilled_generation_rejects_robolab_policy(make_cosmos3_pipeline) -> N
        pipeline._forward_robolab_policy(make_sampling_params(), None, 0.0)


-def test_forward_threads_request_id_to_robolab(make_cosmos3_pipeline) -> None:
-    pipeline = make_cosmos3_pipeline()
-    robolab_inputs = object()
-    captured: dict[str, Any] = {}
-    expected = object()
-    pipeline._build_robolab_policy_inputs = lambda sp, prompt, request_id: robolab_inputs
-
-    def fake_forward_robolab(sp, inputs, pipeline_start, session_id=None):
-        del sp, inputs, pipeline_start
-        captured["session_id"] = session_id
-        return expected
-
-    pipeline._forward_robolab_policy = fake_forward_robolab
-    request = SimpleNamespace(
-        prompts=["policy"],
-        sampling_params=make_sampling_params(),
-        request_id="robolab-request-7",
-    )
-
-    assert pipeline.forward(request) is expected
-    assert captured["session_id"] == "robolab-request-7"
-
-
@pytest.mark.parametrize(
    ("prompt", "sampling_params", "message"),
    [
@@ -619,7 +595,6 @@ def _make_od_config(
    return SimpleNamespace(
        enable_cpu_offload=False,
        enable_diffusion_pipeline_profiler=False,
-        enable_session_state_manager=False,
        model="/nonexistent/model/path",
        dtype=torch.float32,
        flow_shift=None,
@@ -1698,32 +1673,6 @@ def test_diffuse_covers_cfg_i2v_and_multimodal_steps(make_cosmos3_pipeline) -> N
    torch.testing.assert_close(action_result, torch.full((), 44.0).expand_as(action_result))


-def test_diffuse_drops_session_when_progress_iteration_fails(make_cosmos3_pipeline) -> None:
-    pipeline = make_cosmos3_pipeline()
-    pipeline._use_session_state = True
-    pipeline._memory_manager = SessionStateManager()
-
-    class FailingProgress:
-        def __iter__(self):
-            raise RuntimeError("progress failed before first step")
-
-    pipeline.progress_bar = lambda timesteps: FailingProgress()
-    with pytest.raises(RuntimeError, match="progress failed"):
-        pipeline.diffuse(
-            latents=torch.zeros(1, 2, 1, 1, 1),
-            timesteps=torch.tensor([7]),
-            cond_ids=_ids(2),
-            cond_mask=_mask(),
-            uncond_ids=_ids(1),
-            uncond_mask=_mask(),
-            guidance_scale=1.0,
-            shared_kwargs={"video_shape": (1, 1, 1), "fps": 24.0},
-            session_id="request-that-fails",
-        )
-
-    assert "request-that-fails" not in pipeline._memory_manager
-
-
 def test_diffuse_transfer_applies_control_cfg(make_cosmos3_pipeline, sequential_cfg_parallel) -> None:
    pipeline = make_cosmos3_pipeline()
    latents = torch.zeros(1, 2, 1, 1, 1)
@@ -1753,28 +1702,6 @@ def test_diffuse_transfer_applies_control_cfg(make_cosmos3_pipeline, sequential_
    torch.testing.assert_close(result, torch.full_like(latents, 254.0))


-def test_diffuse_transfer_rejects_session_state_manager(make_cosmos3_pipeline) -> None:
-    pipeline = make_cosmos3_pipeline()
-    pipeline._use_session_state = True
-
-    with pytest.raises(NotImplementedError, match="richer cache keys"):
-        pipeline.diffuse_transfer(
-            latents=torch.zeros(1, 2, 1, 1, 1),
-            timesteps=torch.tensor([7]),
-            cond_ids=_ids(2),
-            cond_mask=_mask(),
-            uncond_ids=_ids(1),
-            uncond_mask=_mask(),
-            guidance_scale=1.0,
-            control_guidance=1.0,
-            control_guidance_interval=None,
-            control_latents=[],
-            shared_kwargs={},
-            velocity_mask=torch.ones(1, 1, 1, 1, 1),
-            condition_latents=torch.zeros(1, 2, 1, 1, 1),
-        )
-
-
 def test_diffuse_transfer_skips_idle_cfg_branches(make_cosmos3_pipeline, sequential_cfg_parallel) -> None:
    latents = torch.zeros(1, 2, 1, 1, 1)
    velocity_mask = torch.ones(1, 1, 1, 1, 1)
@@ -1,447 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-from types import SimpleNamespace
-
-import pytest
-import torch
-from transformers.utils.generic import ModelOutput
-
-import vllm_omni.diffusion.models.hunyuan_image3.pipeline_hunyuan_image3 as pipeline_module
-from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
-from vllm_omni.diffusion.diffusion_kv.request import DiffusionKVRequest
-from vllm_omni.diffusion.models.hunyuan_image3.hunyuan_image3_tokenizer import TokenizerEncodeOutput
-from vllm_omni.diffusion.models.hunyuan_image3.hunyuan_image3_transformer import (
-    ImageInfo,
-    JointImageInfo,
-)
-from vllm_omni.diffusion.models.hunyuan_image3.pipeline_hunyuan_image3 import (
-    HunyuanImage3Pipeline,
-    get_hunyuan_image_3_pre_process_func,
-)
-from vllm_omni.diffusion.models.hunyuan_image3.request_layout import (
-    HunyuanPreparedLayout,
-    build_hunyuan_diffusion_kv_requests,
-    extract_hunyuan_prompt_inputs,
-    hunyuan_num_image_tokens,
-    normalize_hunyuan_cot_text,
-    prepare_hunyuan_layout,
-)
-from vllm_omni.diffusion.request import OmniDiffusionRequest
-from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
-
-
-def test_dense_legacy_preprocess_does_not_initialize_layout_tokenizer(monkeypatch) -> None:
-    hf_config = SimpleNamespace(vae_downsample_factor=(8, 8), patch_size=2)
-    image_processor = SimpleNamespace(vision_encoder_processor=SimpleNamespace(patch_size=1))
-    monkeypatch.setattr(pipeline_module, "get_config", lambda *_args, **_kwargs: hf_config)
-    monkeypatch.setattr(pipeline_module, "HunyuanImage3ImageProcessor", lambda _config: image_processor)
-    monkeypatch.setattr(
-        pipeline_module,
-        "TokenizerWrapper",
-        lambda _model: pytest.fail("dense_legacy must not initialize the Diffusion KV tokenizer"),
-    )
-
-    get_hunyuan_image_3_pre_process_func(
-        SimpleNamespace(model="model", diffusion_kv_mode=DiffusionKVCacheMode.DENSE_LEGACY)
-    )
-
-
-class _FakeTokenizerWrapper:
-    def __init__(self, *, prefix_lens: list[int]) -> None:
-        self.prefix_lens = prefix_lens
-        self.calls: list[dict] = []
-        self.pad_token_id = 0
-        self.eos_token_id = 2
-        self.boi_token_id = 3
-        self.end_recaption_token_id = 4
-        self.end_answer_token_id = 5
-        self.special_token_map = {f"<img_ratio_{index}>": 100 + index for index in range(33)}
-
-    def apply_chat_template(self, **kwargs):
-        self.calls.append(kwargs)
-        rows = len(self.prefix_lens)
-        has_cond_image = kwargs.get("batch_cond_image_info") is not None
-        seq_lens = [prefix_len + 20 for prefix_len in self.prefix_lens]
-        padded_seq_len = max(seq_lens)
-        positions = torch.arange(padded_seq_len)
-        joint_image_slices = [[slice(1, 3), slice(3, 5)] if has_cond_image else [] for _ in range(rows)]
-        gen_image_slices = [[slice(length + 1, length + 17)] for length in self.prefix_lens]
-        all_image_slices = [joint + generated for joint, generated in zip(joint_image_slices, gen_image_slices)]
-        cond_vae_image_mask = (
-            torch.stack([(positions >= 1) & (positions < 3) for _ in range(rows)]) if has_cond_image else None
-        )
-        cond_vit_image_mask = (
-            torch.stack([(positions >= 3) & (positions < 5) for _ in range(rows)]) if has_cond_image else None
-        )
-        sections = []
-        for _ in range(rows):
-            row_sections = []
-            if has_cond_image:
-                row_sections.append(
-                    {
-                        "type": "joint_image",
-                        "token_height": [1, 1],
-                        "token_width": [2, 2],
-                    }
-                )
-            row_sections.append({"type": "gen_image", "token_height": 4, "token_width": 4})
-            sections.append(row_sections)
-        return {
-            "output": TokenizerEncodeOutput(
-                tokens=torch.arange(rows * padded_seq_len, dtype=torch.long).reshape(rows, padded_seq_len),
-                gen_timestep_scatter_index=torch.tensor(self.prefix_lens, dtype=torch.long).reshape(rows, 1),
-                cond_timestep_scatter_index=(torch.zeros(rows, 1, dtype=torch.long) if has_cond_image else None),
-                all_image_slices=all_image_slices,
-                gen_image_mask=torch.stack(
-                    [(positions >= length + 1) & (positions < length + 17) for length in self.prefix_lens]
-                ),
-                cond_vae_image_mask=cond_vae_image_mask,
-                cond_vit_image_mask=cond_vit_image_mask,
-                joint_image_slices=joint_image_slices,
-                gen_image_slices=gen_image_slices,
-                real_pos=torch.tensor(seq_lens, dtype=torch.long).reshape(rows, 1),
-            ),
-            "sections": sections,
-        }
-
-
-class _FakeImageProcessor:
-    def __init__(self, image_token_length: int = 16) -> None:
-        self.image_token_length = image_token_length
-        self.image_sizes: list[tuple[int, int]] = []
-        self.vision_encoder_processor = SimpleNamespace(patch_size=1)
-
-    def build_image_info(self, image_size):
-        self.image_sizes.append(image_size)
-        return ImageInfo(
-            image_type="gen_image",
-            image_width=image_size[1],
-            image_height=image_size[0],
-            token_width=4,
-            token_height=4,
-            image_token_length=self.image_token_length,
-            base_size=1024,
-            ratio_index=0,
-        )
-
-
-def _components(prefix_lens: list[int]):
-    return _FakeTokenizerWrapper(prefix_lens=prefix_lens), _FakeImageProcessor()
-
-
-def _prepare(
-    request: OmniDiffusionRequest,
-    tokenizer: _FakeTokenizerWrapper,
-    image_processor: _FakeImageProcessor,
-) -> HunyuanPreparedLayout:
-    prepared_layout = prepare_hunyuan_layout(
-        request,
-        tokenizer_wrapper=tokenizer,
-        image_processor=image_processor,
-        generation_config=SimpleNamespace(sequence_template="instruct", drop_think=False),
-        image_base_size=1024,
-    )
-    request.prepared_layout = prepared_layout
-    return prepared_layout
-
-
-def _request(
-    *,
-    guidance_scale: float,
-    prompt="draw a cat",
-    request_id: str = "req",
-) -> OmniDiffusionRequest:
-    return OmniDiffusionRequest(
-        prompt=prompt,
-        sampling_params=OmniDiffusionSamplingParams(
-            height=768,
-            width=1024,
-            guidance_scale=guidance_scale,
-            num_inference_steps=4,
-        ),
-        request_id=request_id,
-    )
-
-
-def test_builds_kv_request_lengths_without_model_execution() -> None:
-    tokenizer, image_processor = _components([12])
-    request = _request(guidance_scale=1.0)
-    prepared_layout = _prepare(request, tokenizer, image_processor)
-
-    kv_requests = build_hunyuan_diffusion_kv_requests(request, prepared_layout)
-
-    assert isinstance(request.prepared_layout, HunyuanPreparedLayout)
-    assert all(isinstance(item, DiffusionKVRequest) for item in kv_requests)
-    assert [(item.prefix_len, item.target_len, item.seq_len) for item in kv_requests] == [(12, 17, 32)]
-    assert image_processor.image_sizes == [(768, 1024)]
-    assert tokenizer.calls[0]["sequence_template"] == "instruct"
-    assert tokenizer.calls[0]["cfg_factor"] == 1
-    assert kv_requests[0].block_hashes == []
-    assert kv_requests[0].kv_contexts == ()
-    assert kv_requests[0].skip_reading_prefix_cache is True
-
-
-def test_builds_one_kv_request_per_cfg_row() -> None:
-    tokenizer, image_processor = _components([12, 14])
-    request = _request(guidance_scale=5.0)
-    prepared_layout = _prepare(request, tokenizer, image_processor)
-
-    kv_requests = build_hunyuan_diffusion_kv_requests(request, prepared_layout)
-
-    assert [item.sequence_id for item in kv_requests] == [0, 1]
-    assert [item.prefix_len for item in kv_requests] == [12, 14]
-    assert [item.seq_len for item in kv_requests] == [32, 34]
-    assert tokenizer.calls[0]["cfg_factor"] == 2
-
-
-def _reference_image() -> JointImageInfo:
-    return JointImageInfo(
-        vae_image_info=ImageInfo(
-            image_type="vae",
-            token_width=8,
-            token_height=8,
-            image_token_length=64,
-        ),
-        vision_image_info=ImageInfo(
-            image_type="siglip2",
-            token_width=4,
-            token_height=4,
-            image_token_length=16,
-        ),
-        vision_encoder_kwargs={
-            "spatial_shapes": torch.tensor([4, 4]),
-            "pixel_attention_mask": torch.ones(4, dtype=torch.bool),
-        },
-    )
-
-
-def test_passes_preprocessed_reference_image_geometry_to_tokenizer() -> None:
-    tokenizer, image_processor = _components([20])
-    joint_image = _reference_image()
-    prompt = {
-        "prompt": "edit this image",
-        "additional_information": {"batch_cond_image_info": [joint_image]},
-    }
-    request = _request(guidance_scale=1.0, prompt=prompt)
-    prepared_layout = _prepare(request, tokenizer, image_processor)
-
-    kv_requests = build_hunyuan_diffusion_kv_requests(request, prepared_layout)
-
-    assert tokenizer.calls[0]["batch_cond_image_info"] == [[joint_image]]
-    assert kv_requests[0].prefix_len == 20
-    assert kv_requests[0].target_len == 17
-    assert kv_requests[0].seq_len == 40
-    assert kv_requests[0].kv_contexts == ()
-
-
-def _assert_nested_equal(actual, expected) -> None:
-    if isinstance(expected, torch.Tensor):
-        torch.testing.assert_close(actual, expected)
-    elif isinstance(expected, dict):
-        assert actual.keys() == expected.keys()
-        for key in expected:
-            _assert_nested_equal(actual[key], expected[key])
-    elif isinstance(expected, list | tuple):
-        assert isinstance(actual, type(expected))
-        assert len(actual) == len(expected)
-        for actual_item, expected_item in zip(actual, expected):
-            _assert_nested_equal(actual_item, expected_item)
-    else:
-        assert actual == expected
-
-
-@pytest.mark.parametrize(
-    ("prefix_lens", "guidance_scale", "with_reference_image"),
-    [
-        pytest.param([12], 1.0, False, id="cfg-1"),
-        pytest.param([12, 14], 5.0, False, id="cfg-2"),
-        pytest.param([20], 1.0, True, id="cfg-1-reference-image"),
-        pytest.param([20, 22], 5.0, True, id="cfg-2-reference-image"),
-    ],
-)
-def test_prepared_model_inputs_match_local_tokenization(
-    monkeypatch,
-    prefix_lens: list[int],
-    guidance_scale: float,
-    with_reference_image: bool,
-) -> None:
-    tokenizer, image_processor = _components(prefix_lens)
-    prompt: str | dict = "draw a cat"
-    if with_reference_image:
-        prompt = {
-            "prompt": "edit this image",
-            "additional_information": {"batch_cond_image_info": [_reference_image()]},
-        }
-    request = _request(guidance_scale=guidance_scale, prompt=prompt)
-    prepared_layout = _prepare(request, tokenizer, image_processor)
-
-    prompts, cot_texts, system_prompt, batch_cond_image_info, bot_task = extract_hunyuan_prompt_inputs(
-        [request.prompt],
-        request.sampling_params.extra_args or {},
-        request_id=request.request_id,
-        allow_cond_image=True,
-    )
-    cot_text = (
-        [normalize_hunyuan_cot_text(text) for text in cot_texts]
-        if any(text is not None for text in cot_texts)
-        else None
-    )
-
-    pipeline = object.__new__(HunyuanImage3Pipeline)
-    pipeline._tkwrapper = tokenizer
-    pipeline.image_processor = image_processor
-    pipeline.generation_config = SimpleNamespace(sequence_template="instruct", drop_think=False)
-    pipeline.config = SimpleNamespace(
-        image_base_size=1024,
-        attention_head_dim=2,
-        rope_theta=10000.0,
-    )
-    monkeypatch.setattr(HunyuanImage3Pipeline, "device", property(lambda _self: torch.device("cpu")))
-
-    def fake_encode_cond_image(batch_cond_image_info_list, cfg_factor=1, generator=None):
-        del generator
-        rows = len(batch_cond_image_info_list) * cfg_factor
-        return (
-            torch.arange(rows * 4, dtype=torch.float32).reshape(rows, 1, 2, 2),
-            torch.arange(rows, dtype=torch.float32),
-            torch.arange(rows * 3, dtype=torch.float32).reshape(rows, 3),
-        )
-
-    pipeline._encode_cond_image = fake_encode_cond_image
-
-    def fake_build_batch_2d_rope(*, image_infos, seq_len, **_kwargs):
-        geometry_sum = sum(
-            int(image_slice.start or 0) + int(image_slice.stop or 0) + height + width
-            for row in image_infos
-            for image_slice, (height, width) in row
-        )
-        values = torch.tensor([len(image_infos), seq_len, geometry_sum], dtype=torch.float32)
-        return values, values + 1
-
-    monkeypatch.setattr(pipeline_module, "build_batch_2d_rope", fake_build_batch_2d_rope)
-    common_kwargs = dict(
-        prompt=prompts,
-        cot_text=cot_text,
-        system_prompt=system_prompt,
-        mode="gen_image",
-        guidance_scale=guidance_scale,
-        image_size=(request.sampling_params.height, request.sampling_params.width),
-        generator=[torch.Generator().manual_seed(0)],
-        batch_cond_image_info=batch_cond_image_info,
-        bot_task=bot_task,
-    )
-
-    local_inputs = pipeline.prepare_model_inputs(**common_kwargs)
-    prepared_inputs = pipeline.prepare_model_inputs(**common_kwargs, prepared_layout=prepared_layout)
-
-    comparable_fields = (
-        "input_ids",
-        "position_ids",
-        "custom_pos_emb",
-        "image_mask",
-        "gen_timestep_scatter_index",
-        "cond_vae_images",
-        "cond_timestep",
-        "cond_vae_image_mask",
-        "cond_vit_images",
-        "cond_vit_image_mask",
-        "vit_kwargs",
-        "cond_timestep_scatter_index",
-    )
-    for field in comparable_fields:
-        _assert_nested_equal(prepared_inputs[field], local_inputs[field])
-
-    tokenizer_fields = (
-        "tokens",
-        "gen_image_mask",
-        "cond_vae_image_mask",
-        "cond_vit_image_mask",
-        "gen_timestep_scatter_index",
-        "cond_timestep_scatter_index",
-        "real_pos",
-        "all_image_slices",
-        "joint_image_slices",
-        "gen_image_slices",
-    )
-    for field in tokenizer_fields:
-        _assert_nested_equal(
-            getattr(prepared_inputs["tokenizer_output"], field),
-            getattr(local_inputs["tokenizer_output"], field),
-        )
-
-    local_mask = pipeline._prepare_attention_mask_for_generation(
-        local_inputs["input_ids"],
-        pipeline.generation_config,
-        local_inputs,
-    )
-    prepared_mask = pipeline._prepare_attention_mask_for_generation(
-        prepared_inputs["input_ids"],
-        pipeline.generation_config,
-        prepared_inputs,
-    )
-    torch.testing.assert_close(prepared_mask, local_mask)
-    assert prepared_inputs["full_attn_spans"] == local_inputs["full_attn_spans"]
-
-    num_image_tokens = hunyuan_num_image_tokens(prepared_layout.generated_image_info)
-    local_inputs.update(attention_mask=local_mask, num_image_tokens=num_image_tokens)
-    prepared_inputs.update(attention_mask=prepared_mask, num_image_tokens=num_image_tokens)
-    local_step_inputs = pipeline._update_model_kwargs_for_generation(ModelOutput(), local_inputs)
-    prepared_step_inputs = pipeline._update_model_kwargs_for_generation(ModelOutput(), prepared_inputs)
-
-    for field in ("position_ids", "attention_mask", "gen_timestep_scatter_index", "full_attn_spans"):
-        _assert_nested_equal(prepared_step_inputs[field], local_step_inputs[field])
-
-
-def test_rejects_tokenizer_cfg_row_mismatch() -> None:
-    tokenizer, image_processor = _components([12])
-    request = _request(guidance_scale=5.0)
-    prepared_layout = _prepare(request, tokenizer, image_processor)
-
-    with pytest.raises(ValueError, match="sequence count does not match"):
-        build_hunyuan_diffusion_kv_requests(request, prepared_layout)
-
-
-def test_sender_endpoint_does_not_change_local_kv_request() -> None:
-    tokenizer, image_processor = _components([12])
-    request = _request(guidance_scale=1.0)
-    request.kv_sender_info = {"host": "127.0.0.1", "zmq_port": 5000}
-    prepared_layout = _prepare(request, tokenizer, image_processor)
-
-    kv_requests = build_hunyuan_diffusion_kv_requests(request, prepared_layout)
-
-    assert kv_requests[0].seq_len == 32
-    assert kv_requests[0].num_computed_tokens == 0
-
-
-def test_paged_preprocess_attaches_layout_and_scheduler_kv_requests(monkeypatch) -> None:
-    tokenizer, image_processor = _components([12])
-    hf_config = SimpleNamespace(
-        vae_downsample_factor=(8, 8),
-        patch_size=2,
-        image_base_size=1024,
-    )
-    monkeypatch.setattr(pipeline_module, "get_config", lambda *_args, **_kwargs: hf_config)
-    monkeypatch.setattr(pipeline_module, "HunyuanImage3ImageProcessor", lambda _config: image_processor)
-    monkeypatch.setattr(pipeline_module, "TokenizerWrapper", lambda _model: tokenizer)
-    monkeypatch.setattr(
-        pipeline_module.GenerationConfig,
-        "from_pretrained",
-        lambda _model: SimpleNamespace(sequence_template="instruct", drop_think=False),
-    )
-    preprocess = get_hunyuan_image_3_pre_process_func(
-        SimpleNamespace(model="model", diffusion_kv_mode=DiffusionKVCacheMode.PAGED_SCHEDULER)
-    )
-    request = _request(guidance_scale=1.0)
-
-    prepared_request = preprocess(request)
-
-    assert prepared_request is request
-    assert isinstance(request.prepared_layout, HunyuanPreparedLayout)
-    assert request.diffusion_kv_requests is not None
-    assert [(item.prefix_len, item.target_len, item.seq_len) for item in request.diffusion_kv_requests] == [
-        (12, 17, 32)
-    ]
-    assert len(tokenizer.calls) == 1
@@ -7,10 +7,7 @@ import pytest
 import torch

 import vllm_omni.diffusion.models.hunyuan_image3.pipeline_hunyuan_image3 as hy3_module
-import vllm_omni.diffusion.models.hunyuan_image3.request_layout as hy3_layout_module
 from vllm_omni.diffusion.data import AttentionConfig, AttentionSpec
-from vllm_omni.diffusion.models.hunyuan_image3.hunyuan_image3_tokenizer import TokenizerEncodeOutput
-from vllm_omni.diffusion.models.hunyuan_image3.hunyuan_image3_transformer import ImageInfo
 from vllm_omni.diffusion.models.hunyuan_image3.pipeline_hunyuan_image3 import (
    _STEP_AR_KV,
    _STEP_CFG_FACTOR,
@@ -21,7 +18,6 @@ from vllm_omni.diffusion.models.hunyuan_image3.pipeline_hunyuan_image3 import (
    _STEP_PROMPT_KV,
    HunyuanImage3Pipeline,
 )
-from vllm_omni.diffusion.models.hunyuan_image3.request_layout import HunyuanPreparedLayout
 from vllm_omni.diffusion.worker.input_batch import InputBatch
 from vllm_omni.diffusion.worker.request_batch import DiffusionRequestBatch
 from vllm_omni.diffusion.worker.utils import StepRequestState
@@ -80,72 +76,6 @@ def _sampling_params(**extra_args):
    )


-def _prepared_layout() -> HunyuanPreparedLayout:
-    return HunyuanPreparedLayout(
-        tokenizer_output=TokenizerEncodeOutput(
-            tokens=torch.arange(21).reshape(1, 21),
-            gen_image_mask=torch.ones(1, 21, dtype=torch.bool),
-            gen_timestep_scatter_index=torch.tensor([[4]]),
-            all_image_slices=[[slice(5, 21)]],
-            joint_image_slices=[[]],
-            gen_image_slices=[[slice(5, 21)]],
-            real_pos=torch.tensor([[21]]),
-        ),
-        rope_image_info=[[(slice(5, 21), (4, 4))]],
-        generated_image_info=ImageInfo(
-            image_type="gen_image",
-            image_width=512,
-            image_height=512,
-            token_width=4,
-            token_height=4,
-            image_token_length=16,
-        ),
-    )
-
-
-def test_prepare_model_inputs_reuses_prepared_layout(monkeypatch):
-    pipeline = _pipeline()
-    monkeypatch.setattr(HunyuanImage3Pipeline, "device", property(lambda self: torch.device("cpu")))
-    rope_kwargs = {}
-
-    def fake_build_batch_2d_rope(**kwargs):
-        rope_kwargs.update(kwargs)
-        return torch.zeros(1), torch.zeros(1)
-
-    monkeypatch.setattr(hy3_module, "build_batch_2d_rope", fake_build_batch_2d_rope)
-
-    def fail_apply_chat_template(**_kwargs):
-        pytest.fail("prepared Hunyuan execution must not apply the chat template again")
-
-    pipeline._tkwrapper = SimpleNamespace(
-        apply_chat_template=fail_apply_chat_template,
-        eos_token_id=2,
-        boi_token_id=3,
-        end_recaption_token_id=4,
-        end_answer_token_id=5,
-    )
-    pipeline.config = SimpleNamespace(
-        attention_head_dim=2,
-        rope_theta=10000.0,
-    )
-    prepared = _prepared_layout()
-
-    model_inputs = pipeline.prepare_model_inputs(
-        prompt="prompt",
-        mode="gen_image",
-        guidance_scale=1.0,
-        image_size=(512, 512),
-        device=torch.device("cpu"),
-        generator=[torch.Generator().manual_seed(0)],
-        prepared_layout=prepared,
-    )
-
-    assert model_inputs["tokenizer_output"] is prepared.tokenizer_output
-    assert model_inputs["batch_gen_image_info"] == [prepared.generated_image_info]
-    assert rope_kwargs["image_infos"] is prepared.rope_image_info
-    torch.testing.assert_close(model_inputs["input_ids"], prepared.tokenizer_output.tokens)
-
-
 def test_hunyuan_step_group_key_ignores_step_index_for_later_steps():
    pipeline = _pipeline()
    states = [_state("req-0", 1), _state("req-1", 3)]
@@ -201,13 +131,12 @@ def test_prepare_encode_preserves_normal_hunyuan_bot_task_semantics(
        captured.update(kwargs)
        raise RuntimeError("stop after prepare_model_inputs")

-    monkeypatch.setattr(hy3_layout_module, "get_system_prompt", fake_get_system_prompt)
+    monkeypatch.setattr(hy3_module, "get_system_prompt", fake_get_system_prompt)
    pipeline.prepare_model_inputs = fake_prepare_model_inputs
    state = StepRequestState(
        request_id="req-bot-task",
        sampling=sampling,
        prompt=prompt_item,
-        prepared_layout=_prepared_layout(),
    )

    with pytest.raises(RuntimeError, match="stop after prepare_model_inputs"):
@@ -215,7 +144,6 @@ def test_prepare_encode_preserves_normal_hunyuan_bot_task_semantics(

    assert captured["bot_task"] == expected_model_bot_task
    assert captured["system_prompt_bot_task"] == expected_system_bot_task
-    assert captured["prepared_layout"] is state.prepared_layout


 def test_forward_uses_same_hunyuan_bot_task_semantics(monkeypatch):
@@ -231,22 +159,23 @@ def test_forward_uses_same_hunyuan_bot_task_semantics(monkeypatch):
        captured.update(kwargs)
        raise RuntimeError("stop after prepare_model_inputs")

-    monkeypatch.setattr(hy3_layout_module, "get_system_prompt", fake_get_system_prompt)
+    monkeypatch.setattr(hy3_module, "get_system_prompt", fake_get_system_prompt)
    pipeline.prepare_model_inputs = fake_prepare_model_inputs
-    request = SimpleNamespace(
-        request_id="req-forward-bot-task",
-        sampling_params=_sampling_params(bot_task="think_recaption", use_system_prompt="dynamic"),
-        prompt={"prompt": "prompt", "bot_task": "vanilla"},
-        prepared_layout=_prepared_layout(),
+    req = DiffusionRequestBatch(
+        requests=[
+            SimpleNamespace(
+                request_id="req-forward-bot-task",
+                sampling_params=_sampling_params(bot_task="think_recaption", use_system_prompt="dynamic"),
+                prompt={"prompt": "prompt", "bot_task": "vanilla"},
+            )
+        ]
    )
-    req = DiffusionRequestBatch(requests=[request])

    with pytest.raises(RuntimeError, match="stop after prepare_model_inputs"):
        pipeline.forward(req)

    assert captured["bot_task"] == "think"
    assert captured["system_prompt_bot_task"] == "think"
-    assert captured["prepared_layout"] is request.prepared_layout


 def test_grouped_denoise_rejects_non_sdpa_attention_backend():
@@ -1,133 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-from types import SimpleNamespace
-
-import numpy as np
-import pytest
-import torch
-from PIL import Image
-from torch import nn
-
-from vllm_omni.diffusion.models.lingbot_video.image_condition import (
-    apply_clean_prefix,
-    geometry_align_image,
-    prepare_ti2v_image_condition,
-)
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
-
-
-def _gradient_image(width: int, height: int) -> Image.Image:
-    x = np.linspace(0, 255, width, dtype=np.uint8)[None, :]
-    y = np.linspace(0, 255, height, dtype=np.uint8)[:, None]
-    rgb = np.stack(
-        [
-            np.broadcast_to(x, (height, width)),
-            np.broadcast_to(y, (height, width)),
-            np.full((height, width), 127, dtype=np.uint8),
-        ],
-        axis=-1,
-    )
-    return Image.fromarray(rgb, mode="RGB")
-
-
-@pytest.mark.parametrize("source_size", [(160, 64), (64, 160), (96, 96)])
-def test_geometry_align_image_supports_source_aspect_ratios(source_size):
-    pixel = geometry_align_image(_gradient_image(*source_size), 64, 96)
-
-    assert pixel.shape == (1, 3, 1, 64, 96)
-    assert pixel.dtype == torch.float32
-    assert 0 <= pixel.min() <= pixel.max() <= 1
-
-
-@pytest.mark.parametrize(
-    ("source_size", "target_size"),
-    [((160, 64), (64, 96)), ((64, 160), (96, 64))],
-)
-def test_geometry_align_image_center_crops_without_stretching(source_size, target_size):
-    width, height = source_size
-    target_height, target_width = target_size
-    rgb = np.full((height, width, 3), (255, 0, 0), dtype=np.uint8)
-    if width > target_width:
-        left = (width - target_width) // 2
-        rgb[:, left : left + target_width] = (0, 255, 0)
-    else:
-        top = (height - target_height) // 2
-        rgb[top : top + target_height] = (0, 255, 0)
-
-    pixel = geometry_align_image(
-        Image.fromarray(rgb, mode="RGB"),
-        target_height,
-        target_width,
-    )
-
-    assert pixel.shape == (1, 3, 1, target_height, target_width)
-    expected_green = torch.tensor((0.0, 1.0, 0.0)).view(1, 3, 1, 1, 1)
-    assert torch.equal(pixel, expected_green.expand_as(pixel))
-
-
-class _LatentDistribution:
-    def __init__(self, latent: torch.Tensor):
-        self.latent = latent
-
-    def sample(self, generator=None):
-        del generator
-        return self.latent
-
-
-class _CapturingVAE(nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.anchor = nn.Parameter(torch.zeros(()))
-        self.config = SimpleNamespace(
-            latents_mean=[0.0, 0.0, 0.0],
-            latents_std=[1.0, 1.0, 1.0],
-        )
-        self.encoded_pixel = None
-
-    def encode(self, pixel):
-        self.encoded_pixel = pixel.detach().clone()
-        return SimpleNamespace(latent_dist=_LatentDistribution(pixel))
-
-
-def test_ti2v_vlm_and_vae_paths_share_geometry_aligned_image():
-    vae = _CapturingVAE()
-    condition = prepare_ti2v_image_condition(
-        _gradient_image(160, 64),
-        height=64,
-        width=96,
-        vae=vae,
-        vision_patch_size=16,
-        device=torch.device("cpu"),
-    )
-
-    vae_pixel = (vae.encoded_pixel + 1.0) / 2.0
-    vae_image = vae_pixel[0, :, 0].permute(1, 2, 0).mul(255).byte().numpy()
-    assert condition.vlm_image.size == (96, 64)
-    np.testing.assert_allclose(
-        np.asarray(condition.vlm_image),
-        vae_image,
-        rtol=0,
-        atol=1,
-    )
-
-
-def test_apply_clean_prefix_only_overwrites_condition_frames():
-    latents = torch.arange(20, dtype=torch.float32).reshape(1, 1, 5, 2, 2)
-    original_tail = latents[:, :, 2:].clone()
-    clean = torch.full((1, 1, 2, 2, 2), -3.0)
-
-    returned = apply_clean_prefix(latents, clean)
-
-    assert returned is latents
-    assert torch.equal(latents[:, :, :2], clean)
-    assert torch.equal(latents[:, :, 2:], original_tail)
-
-
-def test_apply_clean_prefix_rejects_incompatible_shapes():
-    with pytest.raises(ValueError, match="shape must match"):
-        apply_clean_prefix(
-            torch.zeros(1, 2, 3, 4, 4),
-            torch.zeros(1, 3, 1, 4, 4),
-        )
@@ -6,10 +6,9 @@ from types import SimpleNamespace
 import numpy as np
 import pytest
 import torch
-from PIL import Image
 from torch import nn

-from vllm_omni.diffusion.request import DUMMY_DIFFUSION_REQUEST_ID, OmniDiffusionRequest
+from vllm_omni.diffusion.request import OmniDiffusionRequest
 from vllm_omni.diffusion.worker.request_batch import DiffusionRequestBatch
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams

@@ -23,8 +22,6 @@ def _make_pipeline():
    nn.Module.__init__(pipeline)
    pipeline.device = torch.device("cpu")
    pipeline.default_negative_prompt = "default negative"
-    pipeline.default_image_negative_prompt = "default image negative"
-    pipeline.img_prompt_template = "<image>"
    pipeline.od_config = SimpleNamespace(flow_shift=None)
    return pipeline

@@ -40,24 +37,17 @@ def test_lingbot_video_pipeline_import_and_registry():
        LingBotVideoPipeline,
        LingBotVideoTransformer3DModel,
        get_lingbot_video_post_process_func,
-        get_lingbot_video_pre_process_func,
-    )
-    from vllm_omni.diffusion.registry import (
-        _DIFFUSION_MODELS,
-        _DIFFUSION_POST_PROCESS_FUNCS,
-        _DIFFUSION_PRE_PROCESS_FUNCS,
    )
+    from vllm_omni.diffusion.registry import _DIFFUSION_MODELS, _DIFFUSION_POST_PROCESS_FUNCS

    assert LingBotVideoPipeline is not None
    assert LingBotVideoTransformer3DModel is not None
-    assert get_lingbot_video_pre_process_func is not None
    assert get_lingbot_video_post_process_func is not None
    assert _DIFFUSION_MODELS["LingBotVideoPipeline"] == (
        "lingbot_video",
        "pipeline_lingbot_video",
        "LingBotVideoPipeline",
    )
-    assert _DIFFUSION_PRE_PROCESS_FUNCS["LingBotVideoPipeline"] == "get_lingbot_video_pre_process_func"
    assert _DIFFUSION_POST_PROCESS_FUNCS["LingBotVideoPipeline"] == "get_lingbot_video_post_process_func"


@@ -68,7 +58,6 @@ def test_component_discovery_declarations():
    assert LingBotVideoPipeline._encoder_modules == ["text_encoder"]
    assert LingBotVideoPipeline._vae_modules == ["vae"]
    assert LingBotVideoPipeline.supports_step_execution is False
-    assert LingBotVideoPipeline.max_outputs_per_prompt == 1


 def test_extra_body_params_include_video_flow_shift_alias():
@@ -80,47 +69,17 @@ def test_extra_body_params_include_video_flow_shift_alias():
    assert "batch_cfg" in params


-def test_preprocess_preserves_geometry_and_converts_rgb(tmp_path):
-    from vllm_omni.diffusion.models.lingbot_video import (
-        get_lingbot_video_pre_process_func,
-    )
+def test_extract_prompt_string_and_mapping():
+    from vllm_omni.diffusion.models.lingbot_video.pipeline_lingbot_video import _extract_prompt

-    image_path = tmp_path / "reference.png"
-    Image.new("L", (48, 32), color=127).save(image_path)
-    request = OmniDiffusionRequest(
-        prompt={
-            "prompt": "a robot walks",
-            "modalities": ["video"],
-            "multi_modal_data": {"image": str(image_path)},
-        },
-        sampling_params=OmniDiffusionSamplingParams(),
-        request_id="lingbot-preprocess-test",
-    )
+    string_req = SimpleNamespace(prompt="a robot waves")
+    assert _extract_prompt(string_req) == ("a robot waves", None)

-    result = get_lingbot_video_pre_process_func(SimpleNamespace())(request)
+    mapping_req = SimpleNamespace(prompt={"prompt": "a robot walks", "negative_prompt": "low quality"})
+    assert _extract_prompt(mapping_req) == ("a robot walks", "low quality")

-    image = result.prompt["multi_modal_data"]["image"]
-    assert image.mode == "RGB"
-    assert image.size == (48, 32)
-
-
-def test_preprocess_marks_internal_image_warmup_as_video():
-    from vllm_omni.diffusion.models.lingbot_video import (
-        get_lingbot_video_pre_process_func,
-    )
-
-    request = OmniDiffusionRequest(
-        prompt={
-            "prompt": "dummy run",
-            "multi_modal_data": {"image": Image.new("RGB", (32, 32))},
-        },
-        sampling_params=OmniDiffusionSamplingParams(),
-        request_id=DUMMY_DIFFUSION_REQUEST_ID,
-    )
-
-    result = get_lingbot_video_pre_process_func(SimpleNamespace())(request)
-
-    assert result.prompt["modalities"] == ["video"]
+    with pytest.raises(TypeError, match="Unsupported LingBot prompt type"):
+        _extract_prompt(SimpleNamespace(prompt=["not", "supported"]))


 def test_check_inputs_accepts_t2v_shapes_and_rejects_invalid_values():
@@ -145,59 +104,6 @@ def test_postprocess_keeps_torch_by_default_and_converts_np_when_requested():
    array = post(frames, SimpleNamespace(output_type="np"))
    assert isinstance(array, np.ndarray)
    assert array.shape == (2, 4, 4, 3)
-    video = post({"video": frames}, SimpleNamespace(output_type="pt"))
-    assert set(video) == {"video"}
-    assert video["video"] is frames
-    image = post(
-        {"image": torch.ones(4, 4, 3)},
-        SimpleNamespace(output_type="pt"),
-    )
-    assert set(image) == {"image"}
-    assert isinstance(image["image"], np.ndarray)
-    assert image["image"].shape == (4, 4, 3)
-    latent = torch.ones(1, 4, 1, 2, 2)
-    latent_output = post({"image": latent}, SimpleNamespace(output_type="latent"))
-    assert set(latent_output) == {"image"}
-    assert latent_output["image"] is latent
-
-
-def test_postprocess_preserves_image_contract_for_serving():
-    from vllm_omni.diffusion.data import DiffusionOutput
-    from vllm_omni.diffusion.models.lingbot_video import get_lingbot_video_post_process_func
-    from vllm_omni.diffusion.output_formatter import (
-        format_diffusion_outputs,
-        normalize_diffusion_postprocess_output,
-    )
-    from vllm_omni.entrypoints.openai.api_server import _extract_images_from_result
-
-    sampling = OmniDiffusionSamplingParams(
-        num_inference_steps=1,
-        output_type="pt",
-        resolution=64,
-    )
-    request = OmniDiffusionRequest(
-        prompt={"prompt": "a robot", "modalities": ["image"]},
-        sampling_params=sampling,
-        request_id="lingbot-image-contract-test",
-    )
-    raw_output = {"image": torch.ones(8, 12, 3)}
-    processed = get_lingbot_video_post_process_func(SimpleNamespace())(raw_output, sampling)
-    normalized = normalize_diffusion_postprocess_output(processed)
-
-    assert normalized.primary_key == "image"
-    [result] = format_diffusion_outputs(
-        request=request,
-        od_config=SimpleNamespace(model_class_name="LingBotVideoPipeline"),
-        diffusion_output=DiffusionOutput(output=raw_output),
-        output_data=raw_output,
-        postprocess_output=normalized,
-    )
-
-    assert len(result.images) == 1
-    assert isinstance(result.images[0], np.ndarray)
-    endpoint_images = _extract_images_from_result(result)
-    assert len(endpoint_images) == 1
-    assert endpoint_images[0].size == (12, 8)


 def test_forward_resolves_t2v_sampling_and_flow_shift_alias():
@@ -210,11 +116,7 @@ def test_forward_resolves_t2v_sampling_and_flow_shift_alias():

    pipeline._generate = fake_generate
    req = _make_request_batch(
-        {
-            "prompt": "a robot arm",
-            "negative_prompt": "bad hands",
-            "modalities": ["video"],
-        },
+        {"prompt": "a robot arm", "negative_prompt": "bad hands"},
        height=192,
        width=320,
        num_frames=9,
@@ -227,12 +129,10 @@ def test_forward_resolves_t2v_sampling_and_flow_shift_alias():

    out = pipeline.forward(req)

-    assert torch.equal(out.output["video"], torch.zeros(9, 192, 320, 3))
+    assert torch.equal(out.output, torch.zeros(9, 192, 320, 3))
    assert len(calls) == 1
    call = calls[0]
    assert call["prompt"] == "a robot arm"
-    assert call["mode"].value == "t2v"
-    assert call["input_image"] is None
    assert call["negative_prompt"] == "bad hands"
    assert call["height"] == 192
    assert call["width"] == 320
@@ -294,222 +194,6 @@ def test_forward_prefers_shift_over_flow_shift_and_defaults_negative_prompt():
    assert calls[0]["negative_prompt"] == "default negative"


-@pytest.mark.parametrize(
-    ("prompt", "num_frames", "expected_mode", "output_key", "default_negative"),
-    [
-        (
-            {"prompt": "a still robot", "modalities": ["image"]},
-            1,
-            "t2i",
-            "image",
-            "default image negative",
-        ),
-        (
-            {
-                "prompt": "a moving robot",
-                "modalities": ["video"],
-                "multi_modal_data": {"image": Image.new("RGB", (48, 32), color="blue")},
-            },
-            9,
-            "ti2v",
-            "video",
-            "default negative",
-        ),
-    ],
-)
-def test_forward_dispatches_generation_mode_and_output(
-    prompt,
-    num_frames,
-    expected_mode,
-    output_key,
-    default_negative,
-):
-    pipeline = _make_pipeline()
-    calls = []
-
-    def fake_generate(**kwargs):
-        calls.append(kwargs)
-        return torch.zeros(192, 320, 3) if output_key == "image" else torch.zeros(num_frames, 192, 320, 3)
-
-    pipeline._generate = fake_generate
-    output = pipeline.forward(
-        _make_request_batch(
-            prompt,
-            height=192,
-            width=320,
-            num_frames=num_frames,
-            num_inference_steps=2,
-            guidance_scale=3.0,
-            seed=42,
-            output_type="pt",
-        )
-    )
-
-    assert set(output.output) == {output_key}
-    assert calls[0]["mode"].value == expected_mode
-    assert calls[0]["negative_prompt"] == default_negative
-    if expected_mode == "ti2v":
-        assert isinstance(calls[0]["input_image"], Image.Image)
-
-
-def test_batched_cfg_pads_image_conditioned_embeddings_and_masks():
-    from vllm_omni.diffusion.models.lingbot_video.pipeline_lingbot_video import (
-        _batch_cfg_prompt_inputs,
-    )
-
-    positive = torch.ones(1, 7, 4)
-    positive_mask = torch.ones(1, 7, dtype=torch.long)
-    negative = torch.full((1, 9, 4), 2.0)
-    negative_mask = torch.ones(1, 9, dtype=torch.long)
-
-    embeds, mask = _batch_cfg_prompt_inputs(
-        positive,
-        positive_mask,
-        negative,
-        negative_mask,
-    )
-
-    assert embeds.shape == (2, 9, 4)
-    assert mask.shape == (2, 9)
-    assert torch.equal(mask[0], torch.tensor([1, 1, 1, 1, 1, 1, 1, 0, 0]))
-    assert torch.equal(mask[1], torch.ones(9, dtype=torch.long))
-
-
-class _RecordingTransformer(nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.anchor = nn.Parameter(torch.zeros(()))
-        self.config = SimpleNamespace(in_channels=1)
-        self.latent_inputs = []
-
-    def forward(
-        self,
-        latents,
-        timestep,
-        prompt_embeds,
-        *,
-        encoder_attention_mask,
-        return_dict,
-    ):
-        del timestep, prompt_embeds, encoder_attention_mask, return_dict
-        self.latent_inputs.append(latents.detach().clone())
-        return (torch.zeros_like(latents),)
-
-
-class _CorruptingScheduler:
-    sigma_max = 1.0
-    sigma_min = 0.0
-
-    def set_timesteps(self, num_inference_steps, *, device, shift, **kwargs):
-        del num_inference_steps, shift, kwargs
-        self.timesteps = torch.tensor([1000.0, 500.0], device=device)
-
-    def step(
-        self,
-        noise_pred,
-        timestep,
-        latents,
-        *,
-        return_dict,
-        generator,
-    ):
-        del noise_pred, timestep, return_dict, generator
-        return (latents + 7.0,)
-
-
-@pytest.mark.parametrize(
-    ("guidance_scale", "batch_cfg", "expected_prompts", "expected_transformer_calls"),
-    [
-        pytest.param(2.0, False, ["positive", "negative"], 4, id="sequential-cfg"),
-        pytest.param(2.0, True, ["positive", "negative"], 2, id="batched-cfg"),
-        pytest.param(1.0, False, ["positive"], 2, id="cfg-disabled"),
-    ],
-)
-def test_ti2v_reinjects_clean_prefix_across_cfg_modes(
-    guidance_scale,
-    batch_cfg,
-    expected_prompts,
-    expected_transformer_calls,
-):
-    from vllm_omni.diffusion.models.lingbot_video import (
-        LingBotGenerationMode,
-        LingBotImageCondition,
-    )
-
-    pipeline = _make_pipeline()
-    pipeline.transformer = _RecordingTransformer()
-    pipeline.scheduler = _CorruptingScheduler()
-    pipeline.progress_bar = lambda timesteps: timesteps
-    pipeline.prepare_latents = lambda *args, **kwargs: torch.zeros(1, 1, 3, 1, 1)
-    vlm_image = Image.new("RGB", (32, 32), color="red")
-    condition = LingBotImageCondition(
-        vlm_image=vlm_image,
-        clean_latent=torch.full((1, 1, 1, 1, 1), 5.0),
-    )
-    pipeline.prepare_ti2v_image_condition = lambda *args, **kwargs: condition
-    encode_calls = []
-
-    def fake_encode(prompt, *, images, device):
-        del device
-        encode_calls.append((prompt, images))
-        return torch.ones(1, 2, 4), torch.ones(1, 2, dtype=torch.long)
-
-    pipeline.encode_prompt = fake_encode
-
-    latents = pipeline._generate(
-        prompt="positive",
-        mode=LingBotGenerationMode.TI2V,
-        input_image=vlm_image,
-        negative_prompt="negative",
-        height=16,
-        width=16,
-        num_frames=9,
-        num_inference_steps=2,
-        guidance_scale=guidance_scale,
-        shift=3.0,
-        output_type="latent",
-        batch_cfg=batch_cfg,
-    )
-
-    assert [call[0] for call in encode_calls] == expected_prompts
-    assert all(call[1] == [vlm_image] for call in encode_calls)
-    assert len(pipeline.transformer.latent_inputs) == expected_transformer_calls
-    for item in pipeline.transformer.latent_inputs:
-        expected_prefix = condition.clean_latent.expand(item.shape[0], -1, -1, -1, -1)
-        assert torch.equal(item[:, :, :1], expected_prefix)
-    assert torch.equal(latents[:, :, :1], condition.clean_latent)
-    assert torch.equal(latents[:, :, 1:], torch.full((1, 1, 2, 1, 1), 14.0))
-
-
-def test_t2i_decodes_and_returns_the_unique_frame():
-    from vllm_omni.diffusion.models.lingbot_video import LingBotGenerationMode
-
-    pipeline = _make_pipeline()
-    pipeline.transformer = _RecordingTransformer()
-    pipeline.scheduler = _CorruptingScheduler()
-    pipeline.progress_bar = lambda timesteps: timesteps
-    pipeline.prepare_latents = lambda *args, **kwargs: torch.zeros(1, 1, 1, 2, 2)
-    pipeline.encode_prompt = lambda *args, **kwargs: (
-        torch.ones(1, 2, 4),
-        torch.ones(1, 2, dtype=torch.long),
-    )
-    pipeline._decode_latents = lambda latents: torch.ones(1, 16, 16, 3)
-
-    image = pipeline._generate(
-        prompt="a still robot",
-        mode=LingBotGenerationMode.T2I,
-        height=16,
-        width=16,
-        num_frames=1,
-        num_inference_steps=2,
-        guidance_scale=1.0,
-        shift=3.0,
-        output_type="pt",
-    )
-
-    assert image.shape == (16, 16, 3)
-
-
 def test_forward_rejects_multi_request_batches():
    pipeline = _make_pipeline()
    first = OmniDiffusionRequest(
@@ -527,45 +211,6 @@ def test_forward_rejects_multi_request_batches():
        pipeline.forward(DiffusionRequestBatch([first, second]))


-def test_forward_marks_invalid_request_contract_as_client_error():
-    from vllm_omni.errors import OmniClientError
-
-    pipeline = _make_pipeline()
-    request = _make_request_batch(
-        {
-            "prompt": "unsupported image edit",
-            "modalities": ["image"],
-            "multi_modal_data": {"image": Image.new("RGB", (32, 32), color="blue")},
-        },
-        height=192,
-        width=320,
-        num_frames=1,
-    )
-
-    with pytest.raises(OmniClientError, match="does not accept") as exc_info:
-        pipeline.forward(request)
-
-    assert exc_info.value.status_code == 400
-
-
-def test_forward_marks_unsupported_output_count_as_client_error():
-    from vllm_omni.errors import OmniClientError
-
-    pipeline = _make_pipeline()
-    request = _make_request_batch(
-        {"prompt": "motion", "modalities": ["video"]},
-        height=192,
-        width=320,
-        num_frames=9,
-        num_outputs_per_prompt=2,
-    )
-
-    with pytest.raises(OmniClientError, match="one output per prompt") as exc_info:
-        pipeline.forward(request)
-
-    assert exc_info.value.status_code == 400
-
-
 def test_load_weights_rejects_external_weight_stream():
    pipeline = _make_pipeline()

@@ -1,350 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-from types import SimpleNamespace
-
-import pytest
-from PIL import Image
-
-from vllm_omni.diffusion.models.lingbot_video.request_utils import (
-    LingBotGenerationMode,
-    caption_from_lingbot_prompt,
-    normalize_lingbot_num_frames,
-    normalize_lingbot_request,
-    resolve_lingbot_mode,
-    resolve_lingbot_num_frames,
-    resolve_lingbot_output_dimensions,
-    resolve_lingbot_size,
-)
-from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
-
-
-def _request(prompt, **sampling_overrides):
-    return SimpleNamespace(
-        prompt=prompt,
-        sampling_params=OmniDiffusionSamplingParams(**sampling_overrides),
-    )
-
-
-def _normalize(prompt, **sampling_overrides):
-    return normalize_lingbot_request(
-        _request(prompt, **sampling_overrides),
-        default_negative_prompt="video default",
-        default_image_negative_prompt="image default",
-    )
-
-
-@pytest.mark.parametrize(
-    ("prompt", "expected"),
-    [
-        ({"prompt": "still", "modalities": ["image"]}, LingBotGenerationMode.T2I),
-        ({"prompt": "motion", "modalities": ["video"]}, LingBotGenerationMode.T2V),
-        (
-            {
-                "prompt": "motion",
-                "modalities": ["video"],
-                "multi_modal_data": {"image": Image.new("RGB", (8, 8))},
-            },
-            LingBotGenerationMode.TI2V,
-        ),
-    ],
-)
-def test_resolve_lingbot_mode(prompt, expected):
-    assert resolve_lingbot_mode(prompt) is expected
-
-
-@pytest.mark.parametrize(
-    ("prompt", "message"),
-    [
-        (
-            {"prompt": "x", "modalities": ["image"], "multi_modal_data": {"image": Image.new("RGB", (8, 8))}},
-            "does not accept",
-        ),
-        (
-            {
-                "prompt": "x",
-                "modalities": ["video"],
-                "multi_modal_data": {"image": [Image.new("RGB", (8, 8)), Image.new("RGB", (8, 8))]},
-            },
-            "exactly one",
-        ),
-        ({"prompt": "x", "modalities": ["video"], "multi_modal_data": {"video": [1]}}, "reference modalities"),
-        ({"prompt": "x", "multi_modal_data": {"image": Image.new("RGB", (8, 8))}}, "explicitly set"),
-        ({"prompt": "x", "modalities": ["audio"]}, "output modality"),
-    ],
-)
-def test_resolve_lingbot_mode_rejects_invalid_media_combinations(prompt, message):
-    with pytest.raises(ValueError, match=message):
-        resolve_lingbot_mode(prompt)
-
-
-def test_caption_from_lingbot_prompt_preserves_text_and_compact_json():
-    assert caption_from_lingbot_prompt("plain text") == "plain text"
-    assert caption_from_lingbot_prompt({"caption": "caption only", "duration": 4}) == "caption only"
-    assert caption_from_lingbot_prompt({"caption": {"中文": True, "nested": {"value": 2}}}) == (
-        '{"中文":true,"nested":{"value":2}}'
-    )
-    assert (
-        caption_from_lingbot_prompt(
-            {"scene": "海边", "camera": {"move": "pan"}, "duration": 5, "fps": 24, "size": "320x192"}
-        )
-        == '{"scene":"海边","camera":{"move":"pan"}}'
-    )
-
-
-@pytest.mark.parametrize("prompt", [{"duration": 4, "fps": 24}, {"caption": ""}, ""])
-def test_caption_from_lingbot_prompt_rejects_empty_caption(prompt):
-    with pytest.raises(ValueError, match="empty|must not be empty"):
-        caption_from_lingbot_prompt(prompt)
-
-
-@pytest.mark.parametrize(
-    ("num_frames", "expected"),
-    [(1, 1), (2, 5), (4, 5), (5, 5), (96, 97), (98, 101), (121, 121)],
-)
-def test_normalize_lingbot_num_frames_rounds_up_to_4n_plus_1(num_frames, expected):
-    assert normalize_lingbot_num_frames(num_frames) == expected
-
-
-@pytest.mark.parametrize("num_frames", [0, -1, 1.5, "invalid"])
-def test_normalize_lingbot_num_frames_rejects_invalid_values(num_frames):
-    with pytest.raises(ValueError, match="num_frames"):
-        normalize_lingbot_num_frames(num_frames)
-
-
-@pytest.mark.parametrize(
-    ("duration", "fps", "expected"),
-    [(4, 24, 97), (5, 24, 121), (8, 24, 193), (4, 12, 49), (4, 30, 121)],
-)
-def test_resolve_lingbot_num_frames_rounds_up(duration, fps, expected):
-    assert resolve_lingbot_num_frames(duration, fps) == expected
-
-
-@pytest.mark.parametrize(("duration", "fps"), [(0, 24), (-1, 24), (0.01, 24), (1, 0), (1, -1)])
-def test_resolve_lingbot_num_frames_rejects_non_positive_or_empty_results(duration, fps):
-    with pytest.raises(ValueError, match="duration|fps|at least one"):
-        resolve_lingbot_num_frames(duration, fps)
-
-
-@pytest.mark.parametrize(
-    ("resolution", "ratio", "expected"),
-    [
-        ("192p", "1:1", (192, 192)),
-        ("192p", "9:16", (192, 320)),
-        ("192p", "16:9", (320, 192)),
-        ("192p", "3:4", (192, 256)),
-        ("192p", "4:3", (256, 192)),
-        ("480p", "1:1", (480, 480)),
-        ("480p", "9:16", (480, 832)),
-        ("480p", "16:9", (832, 480)),
-        ("480p", "3:4", (480, 640)),
-        ("480p", "4:3", (640, 480)),
-        ("720p", "1:1", (736, 736)),
-        ("720p", "9:16", (736, 1280)),
-        ("720p", "16:9", (1280, 736)),
-        ("720p", "3:4", (736, 960)),
-        ("720p", "4:3", (960, 736)),
-        ("1080p", "1:1", (1088, 1088)),
-        ("1080p", "9:16", (1088, 1920)),
-        ("1080p", "16:9", (1920, 1088)),
-        ("1080p", "3:4", (1088, 1440)),
-        ("1080p", "4:3", (1440, 1088)),
-        ("2k", "1:1", (1440, 1440)),
-        ("2k", "9:16", (1440, 2560)),
-        ("2k", "16:9", (2560, 1440)),
-        ("2k", "3:4", (1440, 1920)),
-        ("2k", "4:3", (1920, 1440)),
-        ("4k", "1:1", (2176, 2176)),
-        ("4k", "9:16", (2176, 3840)),
-        ("4k", "16:9", (3840, 2176)),
-        ("4k", "3:4", (2176, 2880)),
-        ("4k", "4:3", (2880, 2176)),
-    ],
-)
-def test_resolve_lingbot_size_supports_all_official_presets(resolution, ratio, expected):
-    assert resolve_lingbot_size(resolution=resolution, ratio=ratio) == expected
-
-
-def test_resolve_lingbot_size_validates_sources_and_alignment():
-    assert resolve_lingbot_size(size="320x192") == (192, 320)
-    assert resolve_lingbot_size(width=320, height=192) == (192, 320)
-    with pytest.raises(ValueError, match="provided together"):
-        resolve_lingbot_size(width=320)
-    with pytest.raises(ValueError, match="provided together"):
-        resolve_lingbot_size(resolution="192p")
-    with pytest.raises(ValueError, match="mutually exclusive"):
-        resolve_lingbot_size(width=320, height=192, resolution="192p", ratio="9:16")
-    with pytest.raises(ValueError, match="multiples of 16"):
-        resolve_lingbot_size(width=321, height=192)
-
-
-def test_resolve_lingbot_output_dimensions_matches_request_priority():
-    assert resolve_lingbot_output_dimensions(
-        sampling_width=480,
-        sampling_height=480,
-        prompt_fields={"resolution": "720p", "ratio": "16:9"},
-    ) == (736, 1280)
-
-    assert resolve_lingbot_output_dimensions(
-        sampling_width=480,
-        sampling_height=480,
-        prompt_fields={"width": 320, "height": 192},
-    ) == (320, 192)
-
-    assert resolve_lingbot_output_dimensions(
-        sampling_width=320,
-        sampling_height=192,
-    ) == (320, 192)
-
-    assert resolve_lingbot_output_dimensions() == (480, 480)
-
-
-def test_normalize_lingbot_request_uses_mode_defaults_and_preserves_empty_negative():
-    t2i = _normalize(
-        {"prompt": "still", "modalities": ["image"], "negative_prompt": ""},
-        width=320,
-        height=192,
-        num_frames=1,
-    )
-    assert t2i.mode is LingBotGenerationMode.T2I
-    assert t2i.num_frames == 1
-    assert t2i.negative_prompt == ""
-
-    t2v = _normalize(
-        {"prompt": "motion", "modalities": ["video"]},
-        width=320,
-        height=192,
-        num_frames=9,
-    )
-    assert t2v.mode is LingBotGenerationMode.T2V
-    assert t2v.negative_prompt == "video default"
-
-
-def test_normalize_lingbot_request_rejects_explicit_zero_flow_shift():
-    with pytest.raises(ValueError, match="shift.*positive"):
-        _normalize(
-            {"prompt": "still", "modalities": ["image"]},
-            width=320,
-            height=192,
-            num_frames=1,
-            extra_args={"flow_shift": 0},
-        )
-
-
-def test_normalize_lingbot_request_rejects_explicit_zero_width():
-    with pytest.raises(ValueError, match="width"):
-        _normalize(
-            {"prompt": "still", "modalities": ["image"]},
-            width=0,
-            height=192,
-            num_frames=1,
-        )
-
-
-def test_normalize_lingbot_request_rounds_all_video_frame_counts():
-    config = _normalize(
-        {"prompt": "motion", "modalities": ["video"]},
-        width=320,
-        height=192,
-        num_frames=96,
-        fps=24,
-        frame_rate=24,
-    )
-    assert config.num_frames == 97
-
-    config = _normalize(
-        {"prompt": "motion", "modalities": ["video"]},
-        width=320,
-        height=192,
-        num_frames=121,
-        fps=24,
-        frame_rate=24,
-    )
-    assert config.num_frames == 121
-
-
-def test_normalize_lingbot_request_prefers_explicit_frames_over_duration():
-    online = _normalize(
-        {"prompt": "motion", "modalities": ["video"]},
-        width=320,
-        height=192,
-        num_frames=9,
-        fps=24,
-        extra_args={"duration": 5},
-    )
-    assert online.num_frames == 9
-
-    offline = _normalize(
-        {
-            "prompt": {"caption": "motion", "duration": 5, "num_frames": 9},
-            "modalities": ["video"],
-        },
-        width=320,
-        height=192,
-        fps=24,
-    )
-    assert offline.num_frames == 9
-
-
-def test_normalize_lingbot_request_uses_duration_then_model_default():
-    duration = _normalize(
-        {"prompt": {"caption": "motion", "duration": 5}, "modalities": ["video"]},
-        width=320,
-        height=192,
-        fps=24,
-    )
-    assert duration.num_frames == 121
-
-    default = _normalize(
-        {"prompt": "motion", "modalities": ["video"]},
-        width=320,
-        height=192,
-    )
-    assert default.num_frames == 81
-
-
-def test_normalize_lingbot_request_rejects_contract_conflicts():
-    with pytest.raises(ValueError, match="text-to-image.*duration"):
-        _normalize(
-            {"prompt": {"caption": "still", "duration": 4}, "modalities": ["image"]},
-            width=320,
-            height=192,
-            num_frames=1,
-        )
-    with pytest.raises(ValueError, match="text-to-image requires"):
-        _normalize(
-            {"prompt": "still", "modalities": ["image"]},
-            width=320,
-            height=192,
-            num_frames=5,
-        )
-    with pytest.raises(ValueError, match="seconds.*duration"):
-        _normalize(
-            {"prompt": "motion", "modalities": ["video"]},
-            width=320,
-            height=192,
-            num_frames=96,
-            extra_args={"seconds": 4, "duration": 4},
-        )
-
-
-def test_normalize_lingbot_request_model_size_overrides_sampling_dimensions():
-    # A prompt-provided size overrides the sampling width/height.
-    config = _normalize(
-        {"prompt": {"caption": "motion", "size": "320x192"}, "modalities": ["video"]},
-        width=480,
-        height=480,
-        num_frames=81,
-    )
-    assert (config.height, config.width) == (192, 320)
-
-    # Without a prompt size, the sampling dimensions are used.
-    config = _normalize(
-        {"prompt": "motion", "modalities": ["video"]},
-        width=480,
-        height=480,
-        num_frames=81,
-    )
-    assert (config.height, config.width) == (480, 480)
@@ -9,7 +9,6 @@ from unittest.mock import Mock
 import numpy as np
 import pytest
 import torch
-import torch.nn as nn

 pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]

@@ -1466,149 +1465,3 @@ def test_g4_reference_video_metadata_validation(field, value, message, tmp_path)
    metadata[field] = value
    with pytest.raises(ValueError, match=message):
        _validate_reference_video_metadata(metadata, index=0, source=str(tmp_path / "reference.mp4"))
-
-
-_ENCODER_HIDDEN = 4
-_ENCODER_HEAD_DIM = 2
-_ENCODER_NUM_HEADS = 2
-_ENCODER_NUM_KV_HEADS = 1
-_ENCODER_INTERMEDIATE = 4
-
-# One distinct value per checkpoint tensor, none of them a parameter initializer
-# (fused weights start as `torch.empty`, norms as ones). A uniform fill would
-# prove only that every row was written, not that each source landed in its own
-# row range, which is the invariant the fused loaders have to get right.
-_SOURCE_FILL = {
-    "self_attn.q_proj.weight": 3.0,
-    "self_attn.k_proj.weight": 4.0,
-    "self_attn.v_proj.weight": 5.0,
-    "mlp.gate_proj.weight": 6.0,
-    "mlp.up_proj.weight": 7.0,
-    "input_layernorm.weight": 8.0,
-}
-
-_QKV_TARGET = "text_model.layers.0.self_attn.qkv_proj.weight"
-_GATE_UP_TARGET = "text_model.layers.0.mlp.gate_up_proj.weight"
-_NORM_TARGET = "text_model.layers.0.input_layernorm.weight"
-
-
-def _one_layer_text_encoder():
-    """Encoder stub holding both fused weights plus one plain parameter."""
-    from vllm_omni.diffusion.models.minimax_h3.encoder import (
-        MiniMaxH3Qwen3VLEncoder,
-        MiniMaxH3Qwen3VLMergedColumnParallelLinear,
-        MiniMaxH3Qwen3VLQKVParallelLinear,
-        MiniMaxH3Qwen3VLRMSNorm,
-    )
-    from vllm_omni.diffusion.models.minimax_h3.pipeline_minimax_h3 import _SingleRankEncoderGroup
-
-    group = _SingleRankEncoderGroup(0)
-    layer = nn.Module()
-    layer.self_attn = nn.Module()
-    layer.self_attn.qkv_proj = MiniMaxH3Qwen3VLQKVParallelLinear(
-        group,
-        hidden_size=_ENCODER_HIDDEN,
-        num_heads=_ENCODER_NUM_HEADS,
-        num_kv_heads=_ENCODER_NUM_KV_HEADS,
-        head_dim=_ENCODER_HEAD_DIM,
-        dtype=torch.float32,
-    )
-    layer.mlp = nn.Module()
-    layer.mlp.gate_up_proj = MiniMaxH3Qwen3VLMergedColumnParallelLinear(
-        group,
-        input_size=_ENCODER_HIDDEN,
-        intermediate_size=_ENCODER_INTERMEDIATE,
-        dtype=torch.float32,
-    )
-    layer.input_layernorm = MiniMaxH3Qwen3VLRMSNorm(_ENCODER_HIDDEN)
-
-    encoder = object.__new__(MiniMaxH3Qwen3VLEncoder)
-    nn.Module.__init__(encoder)
-    encoder.text_model = nn.Module()
-    encoder.text_model.layers = nn.ModuleList([layer])
-    return encoder
-
-
-def _write_text_encoder_checkpoint(path, *, omit=()):
-    """Write a one-layer Qwen3-VL-named checkpoint, one fill value per source."""
-    import json
-
-    import safetensors.torch
-
-    prefix = "model.language_model.layers.0"
-    q_rows = _ENCODER_NUM_HEADS * _ENCODER_HEAD_DIM
-    kv_rows = _ENCODER_NUM_KV_HEADS * _ENCODER_HEAD_DIM
-    shapes = {
-        "self_attn.q_proj.weight": (q_rows, _ENCODER_HIDDEN),
-        "self_attn.k_proj.weight": (kv_rows, _ENCODER_HIDDEN),
-        "self_attn.v_proj.weight": (kv_rows, _ENCODER_HIDDEN),
-        "mlp.gate_proj.weight": (_ENCODER_INTERMEDIATE, _ENCODER_HIDDEN),
-        "mlp.up_proj.weight": (_ENCODER_INTERMEDIATE, _ENCODER_HIDDEN),
-        "input_layernorm.weight": (_ENCODER_HIDDEN,),
-    }
-    tensors = {f"{prefix}.{source}": torch.full(shape, _SOURCE_FILL[source]) for source, shape in shapes.items()}
-    for source in omit:
-        del tensors[f"{prefix}.{source}"]
-    safetensors.torch.save_file(tensors, str(path / "model.safetensors"))
-    index = {"weight_map": dict.fromkeys(tensors, "model.safetensors")}
-    (path / "model.safetensors.index.json").write_text(json.dumps(index))
-
-
-@pytest.mark.parametrize(
-    ("omitted_sources", "expected_detail", "unreported_target"),
-    [
-        (("self_attn.q_proj.weight",), f"{_QKV_TARGET}: ['q']", _GATE_UP_TARGET),
-        (("self_attn.k_proj.weight",), f"{_QKV_TARGET}: ['k']", _GATE_UP_TARGET),
-        (("self_attn.v_proj.weight",), f"{_QKV_TARGET}: ['v']", _GATE_UP_TARGET),
-        (("mlp.gate_proj.weight",), f"{_GATE_UP_TARGET}: ['gate']", _QKV_TARGET),
-        (("mlp.up_proj.weight",), f"{_GATE_UP_TARGET}: ['up']", _QKV_TARGET),
-        (
-            ("self_attn.q_proj.weight", "self_attn.k_proj.weight", "self_attn.v_proj.weight"),
-            f"{_QKV_TARGET}: ['q', 'k', 'v']",
-            _GATE_UP_TARGET,
-        ),
-    ],
-)
-def test_encoder_load_reports_missing_fused_source_shards(
-    tmp_path, omitted_sources, expected_detail, unreported_target
-):
-    encoder = _one_layer_text_encoder()
-    _write_text_encoder_checkpoint(tmp_path, omit=omitted_sources)
-
-    with pytest.raises(RuntimeError) as excinfo:
-        encoder._load_weights(str(tmp_path))
-
-    message = str(excinfo.value)
-    assert expected_detail in message
-    assert unreported_target not in message
-
-
-def test_encoder_load_rejects_unloaded_plain_param(tmp_path):
-    encoder = _one_layer_text_encoder()
-    _write_text_encoder_checkpoint(tmp_path, omit=("input_layernorm.weight",))
-
-    with pytest.raises(RuntimeError, match=r"weights not loaded.*input_layernorm"):
-        encoder._load_weights(str(tmp_path))
-
-
-def test_encoder_load_places_every_source_in_its_own_rows(tmp_path):
-    encoder = _one_layer_text_encoder()
-    _write_text_encoder_checkpoint(tmp_path)
-
-    encoder._load_weights(str(tmp_path))
-
-    params = dict(encoder.named_parameters())
-    q_rows = _ENCODER_NUM_HEADS * _ENCODER_HEAD_DIM
-    kv_rows = _ENCODER_NUM_KV_HEADS * _ENCODER_HEAD_DIM
-    qkv = params[_QKV_TARGET]
-    gate_up = params[_GATE_UP_TARGET]
-    slices = {
-        "self_attn.q_proj.weight": qkv[:q_rows],
-        "self_attn.k_proj.weight": qkv[q_rows : q_rows + kv_rows],
-        "self_attn.v_proj.weight": qkv[q_rows + kv_rows :],
-        "mlp.gate_proj.weight": gate_up[:_ENCODER_INTERMEDIATE],
-        "mlp.up_proj.weight": gate_up[_ENCODER_INTERMEDIATE:],
-        "input_layernorm.weight": params[_NORM_TARGET],
-    }
-    for source, rows in slices.items():
-        assert torch.equal(rows, torch.full_like(rows, _SOURCE_FILL[source])), source
@@ -19,7 +19,7 @@ MODEL_ENV = "VLLM_TEST_MINIMAX_H3_FL2VA_MODEL"
 def _assert_joint_output(outputs):
    assert len(outputs) == 1
    frames = np.asarray(outputs[0].images[0])
-    assert frames.shape == (107, 256, 448, 3)
+    assert frames.shape == (39, 256, 448, 3)
    multimodal = outputs[0].multimodal_output
    assert multimodal is not None
    assert np.asarray(multimodal["audio"]).shape[1] == 2
@@ -122,58 +122,6 @@ def test_minimax_h3_t2va_fp8_single_gpu_smoke():
                output_type="np",
                extra_args={
                    "task": "t2va",
-                    "duration": 4.0,
-                    "aspect_ratio": "16:9",
-                    "flow_shift": 12.0,
-                    "audio_flow_shift": 3.0,
-                },
-            ),
-            use_tqdm=False,
-        )
-    finally:
-        engine.close()
-
-    _assert_joint_output(outputs)
-
-
-@pytest.mark.skipif(
-    not os.environ.get(MODEL_ENV),
-    reason=f"set {MODEL_ENV} to an authorized FL2VA checkpoint path",
-)
-def test_minimax_h3_t2va_teacache_single_gpu_smoke():
-    import torch
-
-    from vllm_omni.diffusion.data import DiffusionParallelConfig
-    from vllm_omni.entrypoints.omni import Omni
-    from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-
-    if torch.accelerator.device_count() < 1:
-        pytest.skip("MiniMax H3 TeaCache smoke requires a CUDA device")
-
-    engine = Omni(
-        model=os.environ[MODEL_ENV],
-        cache_backend="tea_cache",
-        cache_config={"rel_l1_thresh": 0.17},
-        parallel_config=DiffusionParallelConfig(ulysses_degree=1),
-        trust_remote_code=True,
-        enable_cpu_offload=True,
-        enforce_eager=True,
-    )
-    try:
-        outputs = engine.generate(
-            "A quiet cinematic night scene with matching ambient sound.",
-            OmniDiffusionSamplingParams(
-                height=256,
-                width=448,
-                num_frames=29,
-                fps=24,
-                num_inference_steps=2,
-                seed=42,
-                output_type="np",
-                extra_args={
-                    "task": "t2va",
-                    "duration": 4.0,
-                    "aspect_ratio": "16:9",
                    "flow_shift": 12.0,
                    "audio_flow_shift": 3.0,
                },
@@ -69,7 +69,6 @@ def test_h3_fused_rope_matches_reference_and_preserves_unrotated_dims():

    attention = object.__new__(MiniMaxH3Attention)
    nn.Module.__init__(attention)
-    attention.rot_dim = 96
    attention.rope = RotaryEmbedding(is_neox_style=True, half_head_dim=False)
    attention.rope._forward_method = attention.rope.forward_native

@@ -15,7 +15,6 @@ from vllm_omni.diffusion.data import (
    DiffusionParallelConfig,
    OmniDiffusionConfig,
 )
-from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
 from vllm_omni.diffusion.model_metadata import (
    HUNYUAN_IMAGE3_MAX_INPUT_IMAGES,
    QWEN_IMAGE_EDIT_PLUS_MAX_INPUT_IMAGES,
@@ -125,11 +124,6 @@ class TestCreateDefaultDiffusion:
        assert ea["enforce_eager"] is True
        assert ea["lora_path"] == "/tmp/lora"

-    def test_diffusion_kv_mode_roundtrip(self):
-        od = _roundtrip_diffusion_config(model="x", diffusion_kv_mode="paged_scheduler")
-
-        assert od.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
-

 def test_qwen_image_edit_plus_sets_generic_multimodal_limit():
    od_config = OmniDiffusionConfig(model="Qwen/Qwen-Image-Edit-2511", model_class_name="QwenImageEditPlusPipeline")
@@ -25,7 +25,6 @@ from vllm_omni.diffusion.request import OmniDiffusionRequest
 from vllm_omni.diffusion.sched.interface import (
    CachedRequestData,
    NewRequestData,
-    _AdmissionWaitDecision,
 )
 from vllm_omni.diffusion.sched.interface import (
    DiffusionSchedulerOutput as RealDiffusionSchedulerOutput,
@@ -76,34 +75,6 @@ class MockScheduler:
    def num_running_requests(self) -> int:
        return 0

-    def get_admission_wait_decision(
-        self,
-        *,
-        now: float,
-        dp_concurrent: bool = False,
-    ) -> _AdmissionWaitDecision:
-        del dp_concurrent
-        return _AdmissionWaitDecision(
-            should_wait=True,
-            deadline=now + 0.5,
-            stable_window_s=0.05,
-            max_batch=self.max_num_running_reqs,
-        )
-
-    def should_end_admission_wait(
-        self,
-        decision: _AdmissionWaitDecision,
-        *,
-        now: float,
-        stable_since: float,
-    ) -> bool:
-        waiting = self.num_waiting_requests()
-        return (
-            waiting >= decision.max_batch
-            or (waiting > 0 and now - stable_since >= decision.stable_window_s)
-            or (decision.deadline is not None and now >= decision.deadline)
-        )
-
    def schedule(self) -> DiffusionSchedulerOutput:
        if not self._waiting_queue:
            return DiffusionSchedulerOutput(step_id=self._step_id)
@@ -137,17 +108,6 @@ class MockScheduler:
        pass


-def _make_admission_engine(pre_process_func) -> DiffusionEngine:
-    engine = object.__new__(DiffusionEngine)
-    engine.scheduler = MockScheduler()
-    engine.pre_process_func = pre_process_func
-    engine._out_streams = {}
-    engine._rpc_lock = threading.RLock()
-    engine._cv = threading.Condition(engine._rpc_lock)
-    engine._closed = False
-    return engine
-
-
 class _BatchCapablePipeline:
    supports_request_batch = True

@@ -565,11 +525,6 @@ class TestRequestBatchAdmission:
        with pytest.raises(ValueError, match="request_batch_max_wait_ms"):
            OmniDiffusionConfig(model="test", request_batch_max_wait_ms=-1.0)

-    @pytest.mark.parametrize("bad_wait", [float("nan"), float("inf"), float("-inf")])
-    def test_config_rejects_nonfinite_request_batch_max_wait_ms(self, bad_wait: float) -> None:
-        with pytest.raises(ValueError, match="request_batch_max_wait_ms"):
-            OmniDiffusionConfig(model="test", request_batch_max_wait_ms=bad_wait)
-
    def test_config_normalizes_request_batch_max_wait_ms_to_float(self) -> None:
        config = OmniDiffusionConfig(model="test", request_batch_max_wait_ms=5)

@@ -637,7 +592,7 @@ class TestRequestBatchAdmission:

        start = time.monotonic()
        with engine._cv:
-            engine._wait_for_admission_if_needed_locked()
+            engine._wait_for_request_batch_admission_locked()
        waited_s = time.monotonic() - start

        # Stable-window exit (~50ms), not the full 1000ms deadline.
@@ -728,34 +683,6 @@ async def _consume_final_output(generator):
    return final_output


-@pytest.mark.cpu
-@pytest.mark.parametrize("entrypoint", ["add_request", "async_add_req_and_stream_response"])
-def test_engine_admission_preprocesses_request_once(entrypoint: str) -> None:
-    raw_request = OmniDiffusionRequest(
-        prompt="raw",
-        sampling_params=OmniDiffusionSamplingParams(num_inference_steps=1),
-        request_id="admission",
-    )
-    prepared_request = OmniDiffusionRequest(
-        prompt="prepared",
-        sampling_params=OmniDiffusionSamplingParams(num_inference_steps=1),
-        request_id="admission",
-        prepared_layout=object(),
-    )
-    preprocess_calls = []
-
-    def preprocess(request):
-        preprocess_calls.append(request)
-        return prepared_request
-
-    engine = _make_admission_engine(preprocess)
-
-    getattr(engine, entrypoint)(raw_request)
-
-    assert preprocess_calls == [raw_request]
-    assert engine.scheduler._waiting_queue == [prepared_request]
-
-
@pytest.mark.cpu
@pytest.mark.asyncio
 async def test_async_add_req_and_stream_response():
@@ -127,7 +127,6 @@ def _make_request(tag: str):
        request_id=tag,
        prompt=f"prompt_{tag}",
        sampling_params=SimpleNamespace(**sampling_params),
-        diffusion_kv_requests=None,
    )


@@ -146,7 +145,7 @@ def _make_engine_with_loop(
    engine.executor = _ConcurrencyTrackingExecutor(rpc_delay=rpc_delay)

    sched = RequestScheduler()
-    sched.initialize(SimpleNamespace(max_num_seqs=1, request_batch_max_wait_ms=0.0))
+    sched.initialize(SimpleNamespace(max_num_seqs=1))
    engine.scheduler = sched
    engine.step_execution = False
    engine.supports_request_batch = False
@@ -218,25 +218,6 @@ def _make_compile_runner(
    return runner


-@pytest.mark.core_model
-@pytest.mark.cpu
-def test_update_states_carries_prepared_layout() -> None:
-    runner = _make_runner(cache_backend=None, cache_backend_name=None)
-    request = _make_request()
-    prepared_layout = object()
-    request.prepared_layout = prepared_layout
-    scheduler_output = SimpleNamespace(
-        finished_req_ids=set(),
-        scheduled_new_reqs=[SimpleNamespace(request_id=request.request_id, req=request)],
-        scheduled_cached_reqs=SimpleNamespace(request_ids=[]),
-    )
-
-    states, new_request_ids = DiffusionModelRunner._update_states(runner, scheduler_output)
-
-    assert new_request_ids == [request.request_id]
-    assert states[0].prepared_layout is prepared_layout
-
-
@pytest.mark.core_model
@pytest.mark.cpu
@pytest.mark.parametrize("use_hsdp", [False, True])
@@ -12,8 +12,6 @@ from pytest_mock import MockerFixture

 from vllm_omni.diffusion.data import DiffusionOutput, DiffusionRequestAbortedError
 from vllm_omni.diffusion.diffusion_engine import DiffusionEngine, DiffusionExecutionMode
-from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
-from vllm_omni.diffusion.diffusion_kv.request import DiffusionKVContext, DiffusionKVRequest
 from vllm_omni.diffusion.request import OmniDiffusionRequest
 from vllm_omni.diffusion.sched import (
    BaseScheduler,
@@ -244,86 +242,7 @@ class TestGetRequestBatchSamplingParamsKey:
 class TestRequestScheduler:
    def setup_method(self) -> None:
        self.scheduler: RequestScheduler = RequestScheduler()
-        self.scheduler.initialize(SimpleNamespace(request_batch_max_wait_ms=0.0))
-
-    def test_admission_wait_disabled_with_zero_max_wait(self) -> None:
-        self.scheduler.initialize(SimpleNamespace(request_batch_max_wait_ms=0.0))
-        decision = self.scheduler.get_admission_wait_decision(now=10.0)
-
-        assert decision.should_wait is False
-
-    @pytest.mark.parametrize(
-        ("dp_concurrent", "expected_stable_window_s"),
-        [(False, 0.05), (True, 0.3)],
-    )
-    def test_admission_wait_decision_encodes_coalescing_policy(
-        self,
-        dp_concurrent: bool,
-        expected_stable_window_s: float,
-    ) -> None:
-        self.scheduler.initialize(
-            SimpleNamespace(
-                max_num_seqs=4,
-                request_batch_max_wait_ms=1000.0,
-            )
-        )
-
-        decision = self.scheduler.get_admission_wait_decision(
-            now=10.0,
-            dp_concurrent=dp_concurrent,
-        )
-
-        assert decision.should_wait is True
-        assert decision.deadline == 11.0
-        assert decision.stable_window_s == expected_stable_window_s
-        assert decision.max_batch == 4
-
-    def test_admission_wait_disabled_while_wave_is_running(self) -> None:
-        self.scheduler.initialize(
-            SimpleNamespace(
-                max_num_seqs=1,
-                request_batch_max_wait_ms=1000.0,
-            )
-        )
-        self.scheduler.add_request(_make_request("running"))
-        self.scheduler.schedule()
-
-        decision = self.scheduler.get_admission_wait_decision(now=10.0)
-
-        assert decision.should_wait is False
-
-    def test_admission_wait_end_conditions(self) -> None:
-        self.scheduler.initialize(
-            SimpleNamespace(
-                max_num_seqs=2,
-                request_batch_max_wait_ms=1000.0,
-            )
-        )
-        decision = self.scheduler.get_admission_wait_decision(now=10.0)
-        self.scheduler.add_request(_make_request("a"))
-
-        assert not self.scheduler.should_end_admission_wait(
-            decision,
-            now=10.01,
-            stable_since=10.0,
-        )
-        assert self.scheduler.should_end_admission_wait(
-            decision,
-            now=10.05,
-            stable_since=10.0,
-        )
-        assert self.scheduler.should_end_admission_wait(
-            decision,
-            now=11.0,
-            stable_since=11.0,
-        )
-
-        self.scheduler.add_request(_make_request("b"))
-        assert self.scheduler.should_end_admission_wait(
-            decision,
-            now=10.01,
-            stable_since=10.01,
-        )
+        self.scheduler.initialize(SimpleNamespace())

    def test_single_request_success_lifecycle(self) -> None:
        req_id = self.scheduler.add_request(_make_request("a"))
@@ -340,90 +259,6 @@ class TestRequestScheduler:
        assert self.scheduler.get_request_state(req_id).status == DiffusionRequestStatus.FINISHED_COMPLETED
        assert self.scheduler.has_requests() is False

-    def test_diffusion_kv_request_moves_to_scheduler_state(self) -> None:
-        self.scheduler.initialize(SimpleNamespace(diffusion_kv_mode=DiffusionKVCacheMode.PAGED_SCHEDULER))
-        request = _make_request("diffusion-kv")
-        prepared_layout = object()
-        request.prepared_layout = prepared_layout
-        text_context = DiffusionKVContext(context_id="text", cache_role="cross.text", num_tokens=8)
-        kv_request = DiffusionKVRequest(
-            "diffusion-kv/diffusion-kv/0",
-            sequence_id=0,
-            prefix_len=4,
-            target_len=8,
-            seq_len=16,
-            kv_contexts=(text_context,),
-        )
-        request.diffusion_kv_requests = (kv_request,)
-
-        self.scheduler.add_request(request)
-        state = self.scheduler.get_request_state(request.request_id)
-        scheduler_output = self.scheduler.schedule()
-
-        assert state is not None
-        assert state.diffusion_kv_requests == (kv_request,)
-        assert state.diffusion_kv_requests[0].kv_contexts == (text_context,)
-        assert request.diffusion_kv_requests is None
-        assert scheduler_output.scheduled_new_reqs[0].req.prepared_layout is prepared_layout
-
-    def test_paged_scheduler_rejects_missing_kv_request(self) -> None:
-        self.scheduler.initialize(SimpleNamespace(diffusion_kv_mode=DiffusionKVCacheMode.PAGED_SCHEDULER))
-        request = _make_request("diffusion-kv")
-
-        with pytest.raises(ValueError, match="did not produce DiffusionKVRequest"):
-            self.scheduler.add_request(request)
-
-    @pytest.mark.parametrize(
-        ("owner_name", "field_name"),
-        [
-            ("request", "past_key_values"),
-            ("sampling_params", "past_key_values"),
-            ("sampling_params", "cfg_text_past_key_values"),
-            ("sampling_params", "cfg_img_past_key_values"),
-            ("sampling_params", "cfg_branch_past_key_values"),
-        ],
-    )
-    def test_diffusion_kv_request_rejects_legacy_dense_kv(self, owner_name: str, field_name: str) -> None:
-        self.scheduler.initialize(SimpleNamespace(diffusion_kv_mode=DiffusionKVCacheMode.PAGED_SCHEDULER))
-        request = _make_request("diffusion-kv")
-        owner = request if owner_name == "request" else request.sampling_params
-        setattr(owner, field_name, object())
-        request.diffusion_kv_requests = (
-            DiffusionKVRequest(
-                "diffusion-kv/diffusion-kv/0",
-                sequence_id=0,
-                prefix_len=4,
-                target_len=8,
-                seq_len=16,
-            ),
-        )
-
-        with pytest.raises(ValueError, match=rf"{owner_name}\.{field_name}"):
-            self.scheduler.add_request(request)
-
-    def test_dense_scheduler_rejects_scheduler_only_kv_request(self) -> None:
-        request = _make_request("dense-kv-request")
-        request.diffusion_kv_requests = (
-            DiffusionKVRequest(
-                "dense-kv-request/diffusion-kv/0",
-                sequence_id=0,
-                prefix_len=4,
-                target_len=8,
-                seq_len=16,
-            ),
-        )
-
-        with pytest.raises(ValueError, match="dense_legacy request unexpectedly contains"):
-            self.scheduler.add_request(request)
-
-    def test_dense_scheduler_accepts_legacy_dense_kv(self) -> None:
-        request = _make_request("dense-kv")
-        request.sampling_params.past_key_values = object()
-
-        request_id = self.scheduler.add_request(request)
-
-        assert request_id == request.request_id
-
    def test_error_output_marks_finished_error(self) -> None:
        req_id = self.scheduler.add_request(_make_request("err"))

@@ -727,20 +562,12 @@ class TestDiffusionEngine:
        engine.abort_queue = queue.Queue()

        request = _make_request("engine")
-        prepared_layout = object()
-
-        def preprocess(req):
-            req.prepared_layout = prepared_layout
-            return req
-
-        engine.pre_process_func = mocker.Mock(side_effect=preprocess)
        runner_output = _make_request_output("engine")
        engine.execute_fn = mocker.Mock(return_value=runner_output)

        output = engine.add_req_and_wait_for_response(request)

        assert output is runner_output.result
-        engine.pre_process_func.assert_called_once_with(request)
        engine.execute_fn.assert_called_once()

    def test_supports_scheduler_interface_injection(self, mocker: MockerFixture) -> None:
@@ -804,29 +631,17 @@ class TestDiffusionEngine:
    async def test_step_streaming_raises_aborted_error(self, mocker: MockerFixture) -> None:
        engine = DiffusionEngine.__new__(DiffusionEngine)
        engine._check_and_start_background_loop = mocker.AsyncMock()
-        request = _make_request("req-abort")
-        prepared_layout = object()
-
-        def preprocess(req):
-            req.prepared_layout = prepared_layout
-            return req
-
-        engine.pre_process_func = mocker.Mock(side_effect=preprocess)
+        engine.pre_process_func = None

        async def _stream(_request):
            yield DiffusionOutput(aborted=True, abort_message="Request req-abort aborted.")

-        engine._add_prepared_request = mocker.Mock(return_value=request.request_id)
-        engine.get_output_stream = mocker.Mock(return_value=_stream(None))
+        engine.async_add_req_and_stream_response = mocker.Mock(return_value=_stream(None))

        with pytest.raises(DiffusionRequestAbortedError, match="Request req-abort aborted"):
-            async for _ in engine.step_streaming(request):
+            async for _ in engine.step_streaming(_make_request("req-abort")):
                pass

-        engine.pre_process_func.assert_called_once_with(request)
-        engine._add_prepared_request.assert_called_once_with(request)
-        engine.get_output_stream.assert_called_once_with(request.request_id)
-
    def test_abort_queue_marks_request_finished_aborted(self) -> None:
        engine = DiffusionEngine.__new__(DiffusionEngine)
        engine._rpc_lock = threading.RLock()
@@ -959,32 +774,12 @@ class TestDiffusionEngine:
        with pytest.raises(RuntimeError, match="Dummy run failed: boom"):
            engine._dummy_run()

-    def test_dummy_run_delegates_preprocessing_to_sync_admission(self, mocker: MockerFixture) -> None:
-        engine = DiffusionEngine.__new__(DiffusionEngine)
-        engine.od_config = SimpleNamespace(model_class_name="mock_model", diffusion_load_format="default")
-        engine.pre_process_func = mocker.Mock()
-        engine.add_req_and_wait_for_response = mocker.Mock(return_value=DiffusionOutput(output=None))
-
-        engine._dummy_run()
-
-        engine.pre_process_func.assert_not_called()
-        admitted_request = engine.add_req_and_wait_for_response.call_args.args[0]
-        assert admitted_request.request_id == "dummy_req_id"
-

 class TestStepScheduler:
    def setup_method(self) -> None:
        self.scheduler: StepScheduler = StepScheduler()
        self.scheduler.initialize(SimpleNamespace())

-    def test_admission_wait_is_not_supported(self) -> None:
-        decision = self.scheduler.get_admission_wait_decision(
-            now=10.0,
-            dp_concurrent=True,
-        )
-
-        assert decision.should_wait is False
-
    def test_single_request_step_lifecycle(self) -> None:
        request = _make_step_request("step", num_inference_steps=3)
        req_id = self.scheduler.add_request(request)
@@ -48,7 +48,6 @@ def _mock_request(tag: str):
        request_id=tag,
        prompt=f"prompt_{tag}",
        sampling_params=OmniDiffusionSamplingParams(num_inference_steps=1),
-        diffusion_kv_requests=None,
    )


@@ -228,6 +228,7 @@ def _resolve_deploy_config(config_path: str, run_level: str) -> str:


@pytest.mark.advanced_model
+@pytest.mark.skip(reason="#issue 5475")
@pytest.mark.diffusion
@hardware_test(res={"cuda": "H100", "rocm": "MI325"})
 def test_bagel_img2img_shared_memory_connector(run_level):
@@ -3,10 +3,8 @@

 import importlib.util
 from pathlib import Path
-from types import SimpleNamespace

 import pytest
-import yaml

 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]

@@ -45,113 +43,3 @@ def test_model_display_names_require_string_mapping(tmp_path, monkeypatch):

    with pytest.raises(ValueError, match="MODEL_DISPLAY_NAMES_FILE"):
        generate_examples.load_model_display_names()
-
-
-def test_quantization_examples_keep_source_urls_under_feature_navigation(tmp_path, monkeypatch):
-    nav_file = tmp_path / "docs" / ".nav.yml"
-    nav_file.parent.mkdir(parents=True)
-    nav_file.write_text(
-        yaml.safe_dump(
-            {
-                "nav": [
-                    {
-                        "User Guide": [
-                            {
-                                "Examples": [
-                                    "examples/README.md",
-                                    {"Offline Inference": [{"Old": "user_guide/examples/offline_inference/old.md"}]},
-                                ]
-                            },
-                            {"Features": [{"Quantization": [{"Overview": "user_guide/quantization/overview.md"}]}]},
-                        ]
-                    }
-                ]
-            },
-            sort_keys=False,
-        ),
-        encoding="utf-8",
-    )
-
-    monkeypatch.setattr(generate_examples, "ROOT_DIR", tmp_path)
-    monkeypatch.setattr(generate_examples, "NAV_FILE", nav_file)
-    monkeypatch.setattr(generate_examples, "EXAMPLE_DOC_DIR", tmp_path / "docs/user_guide/examples")
-
-    quantization_example = SimpleNamespace(
-        category="quantization",
-        path=tmp_path / "examples/quantization/check_modelopt_fp8_export.py",
-        nav_title="Check Modelopt FP8 Export",
-    )
-    offline_example = SimpleNamespace(
-        category="offline_inference",
-        path=tmp_path / "examples/offline_inference/demo.py",
-        nav_title="Demo",
-    )
-
-    generate_examples.update_nav_file([quantization_example, offline_example])
-    generate_examples.update_nav_file([quantization_example, offline_example])
-
-    nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
-    user_guide = nav_data["nav"][0]["User Guide"]
-    examples = next(item["Examples"] for item in user_guide if "Examples" in item)
-    features = next(item["Features"] for item in user_guide if "Features" in item)
-    quantization = next(item["Quantization"] for item in features if "Quantization" in item)
-
-    assert not any(isinstance(item, dict) and "Quantization" in item for item in examples)
-    generated_examples = [
-        item[generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE]
-        for item in quantization
-        if generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE in item
-    ]
-    assert len(generated_examples) == 1
-    assert generated_examples[0] == [
-        {"Check Modelopt FP8 Export": "user_guide/examples/quantization/check_modelopt_fp8_export.md"}
-    ]
-
-    # A later build without quantization examples must not leave a stale
-    # generated group in the hand-authored Quantization section.
-    generate_examples.update_nav_file([offline_example])
-    nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
-    user_guide = nav_data["nav"][0]["User Guide"]
-    features = next(item["Features"] for item in user_guide if "Features" in item)
-    quantization = next(item["Quantization"] for item in features if "Quantization" in item)
-    assert not any(
-        isinstance(item, dict) and generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE in item
-        for item in quantization
-    )
-
-
-def test_quantization_examples_are_not_added_to_examples_without_feature_target(tmp_path, monkeypatch, caplog):
-    nav_file = tmp_path / "docs" / ".nav.yml"
-    nav_file.parent.mkdir(parents=True)
-    nav_file.write_text(
-        yaml.safe_dump(
-            {
-                "nav": [
-                    {
-                        "User Guide": [
-                            {"Examples": ["examples/README.md"]},
-                        ]
-                    }
-                ]
-            },
-            sort_keys=False,
-        ),
-        encoding="utf-8",
-    )
-
-    monkeypatch.setattr(generate_examples, "ROOT_DIR", tmp_path)
-    monkeypatch.setattr(generate_examples, "NAV_FILE", nav_file)
-    monkeypatch.setattr(generate_examples, "EXAMPLE_DOC_DIR", tmp_path / "docs/user_guide/examples")
-
-    quantization_example = SimpleNamespace(
-        category="quantization",
-        path=tmp_path / "examples/quantization/check_modelopt_fp8_export.py",
-        nav_title="Check Modelopt FP8 Export",
-    )
-
-    generate_examples.update_nav_file([quantization_example])
-
-    nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
-    examples = nav_data["nav"][0]["User Guide"][0]["Examples"]
-    assert not any(isinstance(item, dict) and "Quantization" in item for item in examples)
-    assert "omitting generated quantization examples from navigation" in caplog.text
@@ -1,16 +1,18 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project

-"""Online serving smoke coverage for the dense LingBot-Video checkpoint."""
+"""
+Online serving smoke for ``robbyant/lingbot-video-dense-1.3b``.
+
+The LingBot dense PR supports text-to-video only, so this module exercises the
+native ``/v1/videos`` path with a small 9-frame request.
+"""

-import json
 import os

 import pytest

-from tests.helpers.assertions import assert_video_first_frame_matches
 from tests.helpers.mark import hardware_marks
-from tests.helpers.media import generate_synthetic_image
 from tests.helpers.runtime import OmniServer, OmniServerParams, OpenAIClientHandler

 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
@@ -41,32 +43,11 @@ def _get_diffusion_feature_cases(model: str):
    ]


-@pytest.mark.slow
+@pytest.mark.core_model
+@pytest.mark.advanced_model
@pytest.mark.diffusion
@pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True)
-def test_text_to_image_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
-    openai_client.send_images_generations_http_request(
-        {
-            "json": {
-                "model": omni_server.model,
-                "prompt": PROMPT,
-                "negative_prompt": NEGATIVE_PROMPT,
-                "size": "320x192",
-                "n": 1,
-                "response_format": "b64_json",
-                "num_inference_steps": 2,
-                "guidance_scale": 3.0,
-                "flow_shift": 3.0,
-                "seed": 42,
-            }
-        }
-    )
-
-
-@pytest.mark.slow
-@pytest.mark.diffusion
-@pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True)
-def test_video_generation_modes_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
+def test_text_to_video_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
    request_config = {
        "model": omni_server.model,
        "form_data": {
@@ -84,18 +65,3 @@ def test_video_generation_modes_001(omni_server: OmniServer, openai_client: Open
        },
    }
    openai_client.send_video_diffusion_request(request_config)
-
-    synthetic_image = generate_synthetic_image(320, 192, force_regenerate=True, seed=42)
-    request_config["form_data"]["prompt"] = "the red block moves slowly while the camera remains fixed"
-    # Keep TI2V dimensions model-scoped until /v1/videos forwards raw reference images.
-    request_config["form_data"].pop("height")
-    request_config["form_data"].pop("width")
-    request_config["form_data"]["extra_params"] = json.dumps({"size": "320x192"}, separators=(",", ":"))
-    request_config["image_reference"] = f"data:image/jpeg;base64,{synthetic_image['base64']}"
-    responses = openai_client.send_video_diffusion_request(request_config)
-    assert responses[0].videos
-    assert_video_first_frame_matches(
-        responses[0].videos[0],
-        synthetic_image["np_array"],
-        max_mean_absolute_error=0.25,
-    )
@@ -4,10 +4,9 @@
 """
 L4 expansion coverage for ``robbyant/lingbot-video-dense-1.3b``.

-This file remains dense-only. Basic T2I/T2V/TI2V serving for both dense and MoE
-checkpoints is covered by ``test_lingbot_video.py`` and
-``test_lingbot_video_moe.py``. Distributed feature rows belong in follow-up
-PRs.
+This file remains dense-only. Basic single-GPU MoE serving is covered by
+``test_lingbot_video_moe.py``; T2I, I2V, TI2V, and multi-GPU feature rows
+belong in follow-up PRs.
 """

 import json
@@ -3,14 +3,11 @@

 """Single-GPU serving smoke for ``robbyant/lingbot-video-moe-30b-a3b``."""

-import json
 import os

 import pytest

-from tests.helpers.assertions import assert_video_first_frame_matches
 from tests.helpers.mark import hardware_marks
-from tests.helpers.media import generate_synthetic_image
 from tests.helpers.runtime import OmniServer, OmniServerParams, OpenAIClientHandler

 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
@@ -41,32 +38,10 @@ def _get_server_cases(model: str):
    ]


-@pytest.mark.slow
-@pytest.mark.diffusion
-@pytest.mark.parametrize("omni_server", _get_server_cases(MODEL), indirect=True)
-def test_text_to_image_moe(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
-    openai_client.send_images_generations_http_request(
-        {
-            "json": {
-                "model": omni_server.model,
-                "prompt": PROMPT,
-                "negative_prompt": NEGATIVE_PROMPT,
-                "size": "320x192",
-                "n": 1,
-                "response_format": "b64_json",
-                "num_inference_steps": 2,
-                "guidance_scale": 3.0,
-                "flow_shift": 3.0,
-                "seed": 42,
-            }
-        }
-    )
-
-
@pytest.mark.full_model
@pytest.mark.diffusion
@pytest.mark.parametrize("omni_server", _get_server_cases(MODEL), indirect=True)
-def test_video_generation_modes_moe(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
+def test_text_to_video_moe(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
    request_config = {
        "model": omni_server.model,
        "form_data": {
@@ -82,18 +57,3 @@ def test_video_generation_modes_moe(omni_server: OmniServer, openai_client: Open
        },
    }
    openai_client.send_video_diffusion_request(request_config)
-
-    synthetic_image = generate_synthetic_image(320, 192, force_regenerate=True, seed=42)
-    request_config["form_data"]["prompt"] = "the red block moves slowly while the camera remains fixed"
-    # Keep TI2V dimensions model-scoped until /v1/videos forwards raw reference images.
-    request_config["form_data"].pop("height")
-    request_config["form_data"].pop("width")
-    request_config["form_data"]["extra_params"] = json.dumps({"size": "320x192"}, separators=(",", ":"))
-    request_config["image_reference"] = f"data:image/jpeg;base64,{synthetic_image['base64']}"
-    responses = openai_client.send_video_diffusion_request(request_config)
-    assert responses[0].videos
-    assert_video_first_frame_matches(
-        responses[0].videos[0],
-        synthetic_image["np_array"],
-        max_mean_absolute_error=0.25,
-    )
@@ -12,7 +12,7 @@ from unittest.mock import Mock
 import pytest
 from omegaconf import OmegaConf
 from pydantic import ValidationError
-from transformers import PretrainedConfig, Qwen3OmniMoeConfig
+from transformers import PretrainedConfig
 from vllm.engine.arg_utils import EngineArgs

 from vllm_omni.config.model import OmniModelConfig
@@ -244,28 +244,6 @@ def test_stage_specific_text_config_override():
    assert omni_config.get_head_size() == talker_head_dim


-def test_non_override_ar_stage_inputs_embeds_size_matches_hidden_size():
-    """A stage without an embedding-size override keeps the default input width."""
-    vllm_config = EngineArgs().create_model_config()
-    vllm_config.hf_config = Qwen3OmniMoeConfig(enable_audio_output=True)
-
-    omni_config = OmniModelConfig.from_vllm_model_config(
-        vllm_config,
-        model_stage="talker",
-        hf_config_name="talker_config",
-    )
-
-    assert (
-        getattr(
-            omni_config.hf_config.talker_config,
-            "embedding_size",
-            None,
-        )
-        is None
-    )
-    assert omni_config.get_inputs_embeds_size() == omni_config.hf_text_config.hidden_size
-
-
 def test_stage_configs_path_field():
    """OmniEngineArgs with stage_configs_path should construct without error."""
    args = OmniEngineArgs(stage_configs_path="/some/path.yaml")
@@ -20,10 +20,6 @@ from vllm_omni.entrypoints.openai.serving_speech import (
    OmniOpenAIServingSpeech,
 )

-# Serving-layer only: the engine is stubbed, so these run on the CPU lane
-# alongside the other tests/entrypoints/openai_api suites.
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-

 def _serving(model_type: str = "audex") -> OmniOpenAIServingSpeech:
    serving = OmniOpenAIServingSpeech.__new__(OmniOpenAIServingSpeech)
@@ -223,17 +223,6 @@ def test_client(mock_async_diffusion):
    return TestClient(app)


-@pytest.fixture
-def lingbot_test_client(test_client):
-    test_client.app.state.stage_configs = [
-        SimpleNamespace(
-            stage_type="diffusion",
-            engine_args={"model_class_name": "LingBotVideoPipeline"},
-        )
-    ]
-    return test_client
-
-
@pytest.fixture
 def async_omni_test_client():
    """Create test client with mocked AsyncOmni engine."""
@@ -3445,17 +3445,16 @@ class TestCosyVoice3Serving:
    def test_cosyvoice3_model_type_detection(self, cosyvoice3_server):
        assert cosyvoice3_server._tts_model_type == "cosyvoice3"
        assert cosyvoice3_server._is_tts is True
+        assert cosyvoice3_server._is_cosyvoice3 is True

    def test_cosyvoice3_stage_registered(self):
-        from vllm_omni.entrypoints.openai.tts_adapters import (
-            all_tts_stage_keys,
-            detect_tts_model_type,
-            resolve_adapter,
+        from vllm_omni.entrypoints.openai.serving_speech import (
+            _COSYVOICE3_TTS_MODEL_STAGES,
+            _TTS_MODEL_STAGES,
        )

-        assert "cosyvoice3_talker" in resolve_adapter("cosyvoice3").stage_keys
-        assert "cosyvoice3_talker" in all_tts_stage_keys()
-        assert detect_tts_model_type("cosyvoice3_talker", None) == "cosyvoice3"
+        assert "cosyvoice3_talker" in _COSYVOICE3_TTS_MODEL_STAGES
+        assert "cosyvoice3_talker" in _TTS_MODEL_STAGES

    def test_validate_cosyvoice3_empty_input(self, cosyvoice3_server):
        request = OpenAICreateSpeechRequest(input="", ref_audio="data:audio/wav;base64,abc", ref_text="hello")
@@ -3602,63 +3601,6 @@ class TestGLMTTSServing:
        load_tokenizer.assert_called_once()


-@pytest.fixture
-def ming_flash_omni_tts_server(mocker: MockerFixture):
-    mocker.patch.object(OmniOpenAIServingSpeech, "_load_supported_speakers", return_value=set())
-    mocker.patch.object(OmniOpenAIServingSpeech, "_load_codec_frame_rate", return_value=None)
-
-    mock_engine_client = mocker.MagicMock()
-    mock_engine_client.errored = False
-    mock_engine_client.model_config = mocker.MagicMock(
-        model="inclusionAI/Ming-omni-tts-0.5B",
-    )
-    mock_engine_client.default_sampling_params_list = [
-        SimpleNamespace(max_tokens=2048, min_tokens=None, extra_args=None)
-    ]
-    mock_engine_client.tts_batch_max_items = 32
-    mock_engine_client.generate = mocker.MagicMock(return_value="generator")
-    mock_engine_client.stage_configs = [
-        SimpleNamespace(
-            engine_args=SimpleNamespace(model_stage="ming_tts"),
-            tts_args={},
-        )
-    ]
-
-    mock_models = mocker.MagicMock()
-    mock_models.is_base_model.return_value = True
-
-    return OmniOpenAIServingSpeech(
-        engine_client=mock_engine_client,
-        models=mock_models,
-        request_logger=mocker.MagicMock(),
-    )
-
-
-class TestMingFlashOmniTTSServing:
-    def test_validate_ming_flash_omni_tts_rejects_ref_text(self, ming_flash_omni_tts_server):
-        request = OpenAICreateSpeechRequest(input="Hello", ref_text="Reference transcript")
-        error = ming_flash_omni_tts_server._validate_tts_request(request)
-        assert error is not None
-        assert "ref_text" in error
-
-    def test_validate_ming_flash_omni_tts_rejects_ref_audio(self, ming_flash_omni_tts_server):
-        request = OpenAICreateSpeechRequest(input="Hello", ref_audio="data:audio/wav;base64,abc")
-        error = ming_flash_omni_tts_server._validate_tts_request(request)
-        assert error is not None
-        assert "ref_audio" in error
-
-    def test_ming_flash_omni_tts_adapter_builds_prompt(self, ming_flash_omni_tts_server, mocker: MockerFixture):
-        ming_flash_omni_tts_server._build_ming_flash_omni_prompt = mocker.MagicMock(
-            return_value={
-                "prompt_token_ids": [1, 2, 3],
-                "additional_information": {"voice": ["test"]},
-            }
-        )
-        request = OpenAICreateSpeechRequest(input="Hello", voice="test")
-        asyncio.run(ming_flash_omni_tts_server._prepare_speech_generation(request))
-        ming_flash_omni_tts_server._build_ming_flash_omni_prompt.assert_called_once()
-
-
 class TestTTSAsyncOffloading:
    """Tests for event-loop-safe offloading of blocking TTS operations."""

@@ -63,6 +63,12 @@ def test_resolve_unknown_returns_none():
    assert resolve_adapter(None) is None


+def test_ming_flash_omni_not_migrated():
+    """ming_flash_omni is intentionally excluded from the adapter migration in
+    this PR; it stays on the legacy inline dispatch in serving_speech.py."""
+    assert resolve_adapter("ming_flash_omni_tts") is None
+
+
 def test_voxcpm2_resolves():
    """VoxCPM2 (the served ``latent_generator`` model) resolves cleanly.

@@ -1,345 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""TTS model detection: registry-driven stage -> model-type resolution.
-
-``serving_speech.py`` used to carry a hand-written 20-branch ladder mapping
-``model_stage``/``model_arch`` to a model-type string, duplicating the
-``stage_keys`` every adapter already declared. Detection is now derived from the
-adapters. ``test_detection_matches_legacy_ladder`` pins the new implementation
-against a verbatim copy of the ladder it replaced, over every input the ladder
-could distinguish, so the migration is checkable rather than reviewable-by-eye.
-"""
-
-import itertools
-
-import pytest
-
-from vllm_omni.entrypoints.openai.tts_adapters import (
-    LEGACY_TTS_DETECTORS,
-    TTS_ADAPTER_REGISTRY,
-    all_tts_stage_keys,
-    detect_tts_model_type,
-    iter_tts_detectors,
-    resolve_adapter,
-    tts_entry_stage_archs,
-)
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-
-
-# --------------------------------------------------------------------------
-# The legacy ladder, copied verbatim from serving_speech.py at 67c54777b
-# (the commit this refactor is based on), with the module constants inlined.
-# Do not "clean up" this function: its value is being a frozen oracle.
-# --------------------------------------------------------------------------
-_LEGACY_MING_TTS_MODEL_ARCHS = {"MingTTSForConditionalGeneration"}
-_LEGACY_VOXTRAL_TTS_MODEL_STAGES = {"audio_generation"}
-_LEGACY_QWEN3_TTS_MODEL_STAGES = {"qwen3_tts"}
-_LEGACY_FISH_TTS_MODEL_STAGES = {"fish_speech_slow_ar"}
-_LEGACY_COSYVOICE3_TTS_MODEL_STAGES = {"cosyvoice3_talker"}
-_LEGACY_OMNIVOICE_TTS_MODEL_STAGES = {"omnivoice_generator"}
-_LEGACY_COVO_AUDIO_MODEL_STAGES = {"fused_thinker_talker"}
-_LEGACY_VOXCPM2_TTS_MODEL_STAGES = {"latent_generator"}
-_LEGACY_MING_TTS_MODEL_STAGES = {"ming_tts"}
-_LEGACY_MOSS_TTS_MODEL_STAGES = {"moss_tts_nano"}
-_LEGACY_MOSS_TTS_FULL_MODEL_STAGES = {"moss_tts", "moss_tts_codec"}
-_LEGACY_MOSS_TTS_LOCAL_MODEL_STAGES = {"moss_tts_local", "moss_tts_local_codec"}
-_LEGACY_HIGGS_AUDIO_V2_TTS_MODEL_STAGES = {"higgs_audio_v2"}
-_LEGACY_HIGGS_V3_TTS_MODEL_STAGES = {"higgs_audio_v3"}
-_LEGACY_GLM_TTS_MODEL_STAGES = {"glm_tts"}
-_LEGACY_STEP_AUDIO2_TTS_MODEL_STAGES = {"step_audio2_thinker"}
-_LEGACY_INDEXTTS2_TTS_MODEL_STAGES = {"indextts2_talker"}
-_LEGACY_AUDEX_TTS_MODEL_STAGES = {"audex_thinker", "audex_omni"}
-_LEGACY_AUDEX_TTA_MODEL_STAGES = {"audex_tta_thinker"}
-
-_LEGACY_TTS_MODEL_STAGES = (
-    _LEGACY_VOXTRAL_TTS_MODEL_STAGES
-    | _LEGACY_QWEN3_TTS_MODEL_STAGES
-    | _LEGACY_FISH_TTS_MODEL_STAGES
-    | _LEGACY_COSYVOICE3_TTS_MODEL_STAGES
-    | _LEGACY_OMNIVOICE_TTS_MODEL_STAGES
-    | _LEGACY_HIGGS_AUDIO_V2_TTS_MODEL_STAGES
-    | _LEGACY_HIGGS_V3_TTS_MODEL_STAGES
-    | _LEGACY_COVO_AUDIO_MODEL_STAGES
-    | _LEGACY_VOXCPM2_TTS_MODEL_STAGES
-    | _LEGACY_MING_TTS_MODEL_STAGES
-    | _LEGACY_MOSS_TTS_MODEL_STAGES
-    | _LEGACY_MOSS_TTS_FULL_MODEL_STAGES
-    | _LEGACY_MOSS_TTS_LOCAL_MODEL_STAGES
-    | _LEGACY_GLM_TTS_MODEL_STAGES
-    | _LEGACY_STEP_AUDIO2_TTS_MODEL_STAGES
-    | _LEGACY_INDEXTTS2_TTS_MODEL_STAGES
-    | _LEGACY_AUDEX_TTS_MODEL_STAGES
-    | _LEGACY_AUDEX_TTA_MODEL_STAGES
-)
-
-
-def _legacy_detect(model_stage, model_arch):
-    if model_arch == "VoxCPM2TalkerForConditionalGeneration":
-        return "voxcpm2"
-    if model_stage in _LEGACY_QWEN3_TTS_MODEL_STAGES:
-        return "qwen3_tts"
-    if model_stage in _LEGACY_VOXTRAL_TTS_MODEL_STAGES:
-        return "voxtral_tts"
-    if model_stage in _LEGACY_FISH_TTS_MODEL_STAGES:
-        return "fish_tts"
-    if model_stage in _LEGACY_COSYVOICE3_TTS_MODEL_STAGES:
-        return "cosyvoice3"
-    if model_stage in _LEGACY_OMNIVOICE_TTS_MODEL_STAGES:
-        return "omnivoice"
-    if model_stage in _LEGACY_COVO_AUDIO_MODEL_STAGES:
-        if model_arch and "CovoAudio" in model_arch:
-            return "covo_audio"
-    if model_stage in _LEGACY_VOXCPM2_TTS_MODEL_STAGES:
-        return "voxcpm2"
-    if model_stage in _LEGACY_MING_TTS_MODEL_STAGES:
-        return "ming_flash_omni_tts"
-    if model_arch in _LEGACY_MING_TTS_MODEL_ARCHS:
-        return "ming_tts"
-    if model_stage in _LEGACY_MOSS_TTS_MODEL_STAGES:
-        return "moss_tts_nano"
-    if model_stage in _LEGACY_MOSS_TTS_FULL_MODEL_STAGES:
-        return "moss_tts"
-    if model_stage in _LEGACY_MOSS_TTS_LOCAL_MODEL_STAGES:
-        return "moss_tts"
-    if model_stage in _LEGACY_HIGGS_AUDIO_V2_TTS_MODEL_STAGES:
-        return "higgs_audio_v2"
-    if model_stage in _LEGACY_HIGGS_V3_TTS_MODEL_STAGES:
-        return "higgs_audio_v3"
-    if model_stage in _LEGACY_GLM_TTS_MODEL_STAGES:
-        return "glm_tts"
-    if model_stage in _LEGACY_STEP_AUDIO2_TTS_MODEL_STAGES:
-        return "step_audio2"
-    if model_stage in _LEGACY_INDEXTTS2_TTS_MODEL_STAGES:
-        return "indextts2"
-    if model_stage in _LEGACY_AUDEX_TTS_MODEL_STAGES:
-        return "audex"
-    if model_stage in _LEGACY_AUDEX_TTA_MODEL_STAGES:
-        return "audex_tta"
-    return None
-
-
-# Every ``model_stage`` value any in-tree pipeline emits, plus any stage key an
-# adapter claims, so the parametrization below covers the real deployment space
-# rather than a hand-picked subset. Refresh the pipeline half with:
-#   grep -rhoE 'model_stage="[^"]+"' --include='pipeline*.py' vllm_omni/model_executor/ \
-#     | sed 's/model_stage="//;s/"$//' | sort -u
-# ``test_pipeline_stage_list_is_complete`` enforces the adapter half.
-_PIPELINE_STAGES = [
-    "AR",
-    "ar",
-    "asr",
-    "audex_code2wav",
-    "audex_omni",
-    "audex_thinker",
-    "audex_tta_thinker",
-    "audex_xcodec",
-    "audio_generation",
-    "audio_tokenizer",
-    "audio_vae",
-    "aura",
-    "code2wav",
-    "cosyvoice3_code2wav",
-    "cosyvoice3_talker",
-    "dac_decoder",
-    "diffusion",
-    "dit",
-    "fish_speech_slow_ar",
-    "fused_thinker_talker",
-    "glm_tts",
-    "glm_tts_dit",
-    "higgs_audio_v2",
-    "higgs_audio_v3",
-    "indextts2_s2mel_decoder",
-    "indextts2_talker",
-    "latent_generator",
-    "llm",
-    "ming_tts",
-    "moss_tts",
-    "moss_tts_codec",
-    "moss_tts_local",
-    "moss_tts_local_codec",
-    "moss_tts_nano",
-    # Claimed by the OmniVoice adapter but emitted by no pipeline: OmniVoice is
-    # served through the diffusion path (``OmniOpenAIServingSpeech.for_diffusion``
-    # sets ``_tts_model_type`` directly and leaves ``_tts_stage`` None), so
-    # detection is never consulted for it. The key is vestigial in the adapter
-    # exactly as it was in the deleted ladder; kept here so detection is still
-    # exercised on it.
-    "omnivoice_generator",
-    "qwen3_tts",
-    "step_audio2_thinker",
-    "talker",
-    "thinker",
-    "token2audio",
-    "token2image",
-    "token2text",
-    "token2wav",
-    "tts",
-]
-
-_STAGES = [*_PIPELINE_STAGES, None, "vae", "not_a_real_stage"]
-_ARCHS = [
-    None,
-    "VoxCPM2TalkerForConditionalGeneration",
-    "MingTTSForConditionalGeneration",
-    "CovoAudioForConditionalGeneration",
-    "MyCovoAudioThing",
-    "Qwen3TTSForConditionalGeneration",
-]
-
-#: Architectures that no adapter claims. Paired with any stage key these are
-#: inert, so the full cross product is meaningful for them.
-_UNCLAIMED_ARCHS = [None, "Qwen3TTSForConditionalGeneration"]
-
-#: Architectures a detector matches on. Pairing one of these with *another*
-#: model's stage key describes a deployment no pipeline can produce (the
-#: architecture comes from the checkpoint, the stage key from the pipeline
-#: definition), and the two implementations deliberately disagree there —
-#: see ``test_arch_matching_is_a_fallback_not_an_override``.
-_CLAIMED_ARCH_CASES = [
-    # Ming dense: its AR stage is the generic ``llm``.
-    ("llm", "MingTTSForConditionalGeneration"),
-    ("audio_vae", "MingTTSForConditionalGeneration"),
-    (None, "MingTTSForConditionalGeneration"),
-    # Ming flash-omni owns the ``ming_tts`` stage key and must win it.
-    ("ming_tts", "MingTTSForConditionalGeneration"),
-    # VoxCPM2: talker architecture plus its own stage key.
-    ("latent_generator", "VoxCPM2TalkerForConditionalGeneration"),
-    (None, "VoxCPM2TalkerForConditionalGeneration"),
-    # CoVo shares ``fused_thinker_talker`` with non-CoVo fused deployments.
-    ("fused_thinker_talker", "CovoAudioForConditionalGeneration"),
-    ("fused_thinker_talker", "MyCovoAudioThing"),
-    ("fused_thinker_talker", None),
-    ("fused_thinker_talker", "Qwen3TTSForConditionalGeneration"),
-]
-
-_REACHABLE = list(itertools.product(_STAGES, _UNCLAIMED_ARCHS)) + _CLAIMED_ARCH_CASES
-
-
-@pytest.mark.parametrize(("model_stage", "model_arch"), _REACHABLE)
-def test_detection_matches_legacy_ladder(model_stage, model_arch):
-    """Registry detection is identical to the ladder it replaced.
-
-    Covers every ``model_stage`` any in-tree pipeline emits (``_PIPELINE_STAGES``,
-    plus negatives) against every architecture no adapter claims, and each
-    claimed architecture against the stage keys it really ships with. Pairing a
-    claimed architecture with an unrelated model's stage key is excluded because
-    no pipeline can produce it, and is covered separately by
-    ``test_arch_matching_is_a_fallback_not_an_override``.
-    """
-    assert detect_tts_model_type(model_stage, model_arch) == _legacy_detect(model_stage, model_arch)
-
-
-def test_arch_matching_is_a_fallback_not_an_override():
-    """The one deliberate divergence from the ladder, pinned.
-
-    The ladder tested Ming's architecture at a fixed position partway down, so a
-    Ming-architecture model deployed under *another* model's stage key resolved
-    to ``ming_tts`` if that key was checked below Ming, and to the other model if
-    above. Detection now treats an architecture-only match as a fallback that
-    runs after every adapter owning a real stage key, so the stage key always
-    wins. That is both self-consistent and unreachable in practice: a
-    checkpoint's architecture and a pipeline's stage key cannot be mixed across
-    models.
-    """
-    assert detect_tts_model_type("audex_omni", "MingTTSForConditionalGeneration") == "audex"
-    assert _legacy_detect("audex_omni", "MingTTSForConditionalGeneration") == "ming_tts"
-    # Where the two real Ming deployments live, they agree.
-    assert detect_tts_model_type("llm", "MingTTSForConditionalGeneration") == "ming_tts"
-    assert detect_tts_model_type("ming_tts", "MingTTSForConditionalGeneration") == "ming_flash_omni_tts"
-
-
-def test_stage_keys_cover_legacy_stage_set():
-    """No stage key was dropped when the module constants were deleted."""
-    assert all_tts_stage_keys() == frozenset(_LEGACY_TTS_MODEL_STAGES)
-
-
-def test_pipeline_stage_list_is_complete():
-    """``_PIPELINE_STAGES`` must still list every stage key adapters claim.
-
-    Guards the parametrization above from silently narrowing: a new adapter
-    whose stage key is missing here would be detected but never exercised.
-    Regenerate the list from the pipelines (see the comment beside it) when a
-    new model lands.
-    """
-    missing = all_tts_stage_keys() - set(_PIPELINE_STAGES)
-    assert not missing, f"stage keys claimed by adapters but absent from _PIPELINE_STAGES: {sorted(missing)}"
-
-
-def test_entry_stage_archs_is_ming_only():
-    """Only Ming dense identifies its entry stage by architecture.
-
-    Widening this set would change which stage ``_find_tts_stage`` selects in
-    mixed deployments — notably VoxCPM2, which declares ``model_archs`` but is
-    found by its ``latent_generator`` stage key.
-    """
-    assert tts_entry_stage_archs() == frozenset({"MingTTSForConditionalGeneration"})
-
-
-def test_every_detected_type_is_adapter_backed_or_declared_legacy():
-    """Detection may only name a model that has an adapter or an explicit
-    :data:`LEGACY_TTS_DETECTORS` entry — never an undeclared string."""
-    legacy_names = {d.name for d in LEGACY_TTS_DETECTORS}
-    for stage, arch in itertools.product(_STAGES, _ARCHS):  # full cross product on purpose
-        detected = detect_tts_model_type(stage, arch)
-        if detected is None:
-            continue
-        assert detected in TTS_ADAPTER_REGISTRY or detected in legacy_names, (
-            f"detection produced undeclared model type {detected!r} for stage={stage!r} arch={arch!r}"
-        )
-
-
-def test_legacy_detectors_have_no_adapter():
-    """A legacy entry that gained an adapter must be deleted from the list."""
-    for detector in LEGACY_TTS_DETECTORS:
-        assert resolve_adapter(detector.name) is None, (
-            f"{detector.name!r} now has an adapter; remove it from LEGACY_TTS_DETECTORS"
-        )
-
-
-def test_no_ambiguous_detectors_at_equal_priority():
-    """Two detectors that can match the same deployment must be ordered.
-
-    This is what makes ``detect_tts_model_type`` independent of adapter import
-    order: any real overlap has to be resolved by an explicit
-    ``detect_priority``, not by whichever module happened to register first.
-    """
-    detectors = iter_tts_detectors()
-    for left, right in itertools.combinations(detectors, 2):
-        if left.detect_priority != right.detect_priority:
-            continue
-        for stage, arch in itertools.product(_STAGES, _ARCHS):
-            assert not (left.matches(stage, arch) and right.matches(stage, arch)), (
-                f"{left.name!r} and {right.name!r} both match stage={stage!r} arch={arch!r} "
-                f"at priority {left.detect_priority}; give one an explicit detect_priority"
-            )
-
-
-def test_detection_order_is_total_and_stable():
-    """Resolution order must not depend on registry insertion order."""
-    keys = [(d.detect_priority, d.name) for d in iter_tts_detectors()]
-    assert keys == sorted(keys)
-    assert len(set(keys)) == len(keys)
-
-
-def test_adapters_declare_at_least_one_match_rule():
-    """An adapter with neither stage keys nor architectures is unreachable."""
-    for name, cls in TTS_ADAPTER_REGISTRY.items():
-        assert cls.stage_keys or cls.model_archs, f"adapter {name!r} declares no stage_keys and no model_archs"
-
-
-def test_audex_omni_requires_speech_decoder():
-    """The Audex omni thinker only serves speech alongside its decoder."""
-    audex = resolve_adapter("audex")
-    assert audex.stage_serves_speech("audex_omni", frozenset({"audex_omni", "audex_code2wav"})) is True
-    assert audex.stage_serves_speech("audex_omni", frozenset({"audex_omni"})) is False
-    # The dedicated TTS thinker is unconditional.
-    assert audex.stage_serves_speech("audex_thinker", frozenset({"audex_thinker"})) is True
-
-
-def test_default_stage_serves_speech_is_unconditional():
-    for name, cls in TTS_ADAPTER_REGISTRY.items():
-        if name == "audex":
-            continue
-        for key in cls.stage_keys:
-            assert cls.stage_serves_speech(key, frozenset({key})) is True
@@ -28,7 +28,6 @@ from vllm_omni.entrypoints.openai.api_server import router
 from vllm_omni.entrypoints.openai.protocol.videos import (
    VideoGenerationRequest,
    VideoGenerationStatus,
-    VideoParams,
    VideoResponse,
 )
 from vllm_omni.entrypoints.openai.serving_video import OmniOpenAIServingVideo
@@ -441,75 +440,6 @@ def test_i2v_video_generation_resizes_input_to_requested_dimensions(test_client,
    assert input_image.size == (96, 64)


-def test_i2v_extra_params_dimensions_preserve_input_image_geometry(test_client, mocker: MockerFixture):
-    image_bytes = _make_test_image_bytes((48, 48))
-    mocker.patch(
-        "vllm_omni.entrypoints.openai.serving_video._encode_video_bytes",
-        return_value=b"fake-video",
-    )
-    response = test_client.post(
-        "/v1/videos",
-        data={
-            "prompt": "A bear playing with yarn.",
-            "extra_params": json.dumps({"width": 96, "height": 64}),
-        },
-        files={"input_reference": ("input.png", image_bytes, "image/png")},
-    )
-
-    assert response.status_code == 200
-    video_id = response.json()["id"]
-    _wait_for_status(test_client, video_id, VideoGenerationStatus.COMPLETED.value)
-
-    engine = test_client.app.state.openai_serving_video._engine_client
-    input_image = engine.captured_prompt["multi_modal_data"]["image"]
-    assert isinstance(input_image, Image.Image)
-    assert input_image.size == (48, 48)
-    sampling_params = engine.captured_sampling_params_list[0]
-    assert sampling_params.extra_args["width"] == 96
-    assert sampling_params.extra_args["height"] == 64
-
-
-@pytest.mark.parametrize(
-    ("generation_request", "expected_num_frames", "expected_duration"),
-    [
-        (
-            VideoGenerationRequest(prompt="top-level frames", seconds="5", num_frames=9),
-            9,
-            5.0,
-        ),
-        (
-            VideoGenerationRequest(prompt="nested frames", video_params=VideoParams(num_frames=9)),
-            9,
-            None,
-        ),
-        (
-            VideoGenerationRequest(prompt="seconds only", seconds="5"),
-            120,
-            5.0,
-        ),
-    ],
-)
-def test_video_generation_bridges_request_fields(generation_request, expected_num_frames, expected_duration):
-    engine = FakeAsyncOmni()
-    handler = OmniOpenAIServingVideo.for_diffusion(
-        diffusion_engine=engine,
-        model_name="Wan-AI/Wan2.2-T2V-A14B-Diffusers",
-    )
-
-    asyncio.run(handler._run_and_extract(generation_request, "field-bridge"))
-
-    sampling = engine.captured_sampling_params_list[0]
-    # Top-level ``seconds`` bridges into extra_args["duration"]; num_frames is
-    # passed through (or derived as seconds x fps when omitted). No private
-    # provenance channel is injected.
-    assert "_vllm_request_context" not in sampling.extra_args
-    assert sampling.num_frames == expected_num_frames
-    if expected_duration is None:
-        assert "duration" not in sampling.extra_args
-    else:
-        assert sampling.extra_args["duration"] == expected_duration
-
-
 def test_i2v_video_generation_with_image_reference_form(test_client, mocker: MockerFixture):
    mocker.patch(
        "vllm_omni.entrypoints.openai.serving_video._encode_video_bytes",
@@ -3,7 +3,6 @@ import re
 from types import SimpleNamespace

 import pytest
-from vllm.lora.request import LoRARequest
 from vllm.sampling_params import RequestOutputKind, SamplingParams

 from tests.helpers.mark import hardware_test
@@ -22,13 +21,10 @@ async def _noop(*args, **kw):
    pass


-def get_fake_add_request(submitted_request_ids, submitted_lora_requests=None):
+def get_fake_add_request(submitted_request_ids):
    async def fake_add_request_async(*, request_id, prompt, sampling_params_list, final_stage_id, **kwargs):
-        lora_request = kwargs.get("lora_request")
        del prompt, sampling_params_list, final_stage_id, kwargs
        submitted_request_ids.append(request_id)
-        if submitted_lora_requests is not None:
-            submitted_lora_requests.append(lora_request)

    return fake_add_request_async

@@ -96,37 +92,6 @@ def test_generate_submits_randomized_id_to_engine():
    asyncio.run(run())


-@pytest.mark.cpu
-def test_generate_forwards_lora_request_to_engine():
-    """Ensure the lora_request passed to generate() reaches add_request_async.
-
-    Regression test for https://github.com/vllm-project/vllm-omni/issues/5369:
-    AsyncOmni.generate() accepted lora_request but silently dropped it when
-    submitting the request, so generation always used the base model.
-    """
-
-    async def run():
-        submitted_ids = []
-        submitted_loras = []
-        omni = get_async_omni_instance(fake_add_request=get_fake_add_request(submitted_ids, submitted_loras))
-
-        lora = LoRARequest(lora_name="test", lora_int_id=1, lora_path="/tmp/fake")
-        async for _ in omni.generate(
-            prompt={"prompt": "test"},
-            request_id="lora-req",
-            sampling_params_list=[SimpleNamespace()],
-            output_modalities=["text"],
-            lora_request=lora,
-        ):
-            pass
-
-        assert len(submitted_ids) == 1
-        assert len(submitted_loras) == 1
-        assert submitted_loras[0] is lora
-
-    asyncio.run(run())
-
-
@pytest.mark.cpu
@pytest.mark.parametrize(
    "req_ids,cancel_prefix,expected_cancel_count",