feat(diffusion): add request-gated VAE fast paths

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

.buildkite/cuda/test-nightly.yml

@@ -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 -m "full_model and cuda" --run-level "full_model"
+          - pytest -s -v tests/e2e/online_serving/test_lingbot_video_moe.py -k "video_generation" -m "full_model and cuda" --run-level "full_model"
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2V · Doc Test"

.buildkite/cuda/test-ready.yml

@@ -47,15 +47,17 @@ steps:
           - timeout 15m pytest -sv tests/diffusion/batching -m 'core_model and cuda' --run-level "core_model"
         mirror_hardwares: l4_1
 
-      - label: "Diffusion · Distributed Test"
+      - label: "Diffusion · Distributed & Attention Test"
         source_file_dependencies:
           - tests/diffusion/distributed/
+          - tests/diffusion/attention/test_attention_sp.py
           - vllm_omni/diffusion/distributed/
-          - vllm_omni/diffusion/attention/parallel/
+          - vllm_omni/diffusion/attention/
           - vllm_omni/diffusion/data.py
           - vllm_omni/diffusion/models/
         commands:
           - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda' --run-level "core_model"
+          - timeout 20m pytest -sv tests/diffusion/attention/test_attention_sp.py -m 'core_model and cuda' --run-level "core_model"
         mirror_hardwares: l4_4
 
       - label: "Diffusion · Model Test"

.claude/skills/add-tts-model/SKILL.md

@@ -220,65 +220,70 @@ See `plan/voxcpm2_native_ar_design.md`.
 
 ### Steps
 
-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.
+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.
 
-   **Point 1** — stage constant (near the top, alongside the other `_*_TTS_MODEL_STAGES` sets):
+   Create `vllm_omni/entrypoints/openai/tts_adapters/your_model.py`:
    ```python
-   _YOUR_MODEL_TTS_MODEL_STAGES = {"your_stage_key"}
+   @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,
+           )
    ```
 
-   **Point 2** — union into `_TTS_MODEL_STAGES`:
-   ```python
-   _TTS_MODEL_STAGES: set[str] = (
-       ...
-       | _YOUR_MODEL_TTS_MODEL_STAGES
-   )
-   ```
+   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 3** — model type detection in `_detect_tts_model_type()`:
-   ```python
-   if model_stage in _YOUR_MODEL_TTS_MODEL_STAGES:
-       return "your_model"
-   ```
+   > **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 4** — validation dispatch in `_validate_tts_request()`:
-   ```python
-   if self._tts_model_type == "your_model":
-       return self._validate_your_model_request(request)
-   ```
+   **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 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
+   **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).
 
-   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.
+   > **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.
 
-   > **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.
+   > **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.
 
 2. **Handle model-specific parameters**:
    - Voice cloning: `ref_audio` encoding and prompt injection
@@ -295,7 +300,7 @@ 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 in serving_speech.py."""
+    """Build prompt with reference audio for voice cloning, called from the adapter."""
     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()]
@@ -321,7 +326,7 @@ 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, `serving_speech` 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, adapter 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` |
@@ -366,7 +371,7 @@ See [vllm-omni-test skill](../vllm-omni-test/SKILL.md) § **Runtime send helpers
 
 ### Deliverables
 
-- Updated `serving_speech.py` with all 5 integration points (single commit)
+- One adapter file under `tts_adapters/` plus its line in the package import block
 - 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)
@@ -514,8 +519,8 @@ Use this checklist when integrating a new TTS model:
 - [ ] README.md written
 
 ### Phase 3: Online Serving
-- [ ] 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)
+- [ ] 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)
 - [ ] Prompt builder handles text input correctly
 - [ ] Voice cloning works (if supported)
 - [ ] All response formats work (wav, mp3, flac, pcm)

.claude/skills/review-pr/SKILL.md

@@ -0,0 +1,231 @@
+---
+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.

.claude/skills/review-pr/agents/openai.yaml

@@ -0,0 +1,4 @@
+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."

.claude/skills/review-pr/references/checks/model-addition-checklist.md

@@ -0,0 +1,121 @@
+# 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.

.claude/skills/review-pr/references/checks/perf-verification.md

@@ -0,0 +1,51 @@
+# 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.

.claude/skills/review-pr/references/checks/test-quality-evaluation.md

@@ -0,0 +1,39 @@
+# 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.

.claude/skills/review-pr/references/checks/tests-docs-checklist.md

@@ -0,0 +1,48 @@
+# 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.

.claude/skills/review-pr/references/checks/verification.md

@@ -0,0 +1,36 @@
+# 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.

.claude/skills/review-pr/references/delivery/maintainer-style-study.md

@@ -0,0 +1,105 @@
+# 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.

.claude/skills/review-pr/references/delivery/review-requests.md

@@ -0,0 +1,99 @@
+# 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.

.claude/skills/review-pr/references/features/communication.md

@@ -0,0 +1,24 @@
+# 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.

.claude/skills/review-pr/references/features/diffusion-acceleration.md

@@ -0,0 +1,26 @@
+# 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.

.claude/skills/review-pr/references/features/infrastructure-performance.md

@@ -0,0 +1,22 @@
+# 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.

.claude/skills/review-pr/references/features/runtime-stage-execution.md

@@ -0,0 +1,24 @@
+# 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.

.claude/skills/review-pr/references/modules/ar-runtime.md

@@ -0,0 +1,22 @@
+# 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.

.claude/skills/review-pr/references/modules/benchmarking.md

@@ -0,0 +1,24 @@
+# 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.

.claude/skills/review-pr/references/modules/cache-management.md

@@ -0,0 +1,22 @@
+# 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.

.claude/skills/review-pr/references/modules/configuration.md

@@ -0,0 +1,24 @@
+# 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.

.claude/skills/review-pr/references/modules/diffusion.md

@@ -0,0 +1,33 @@
+# 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.

.claude/skills/review-pr/references/modules/engine-orchestration.md

@@ -0,0 +1,23 @@
+# 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.

.claude/skills/review-pr/references/modules/entrypoints.md

@@ -0,0 +1,25 @@
+# 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.

.claude/skills/review-pr/references/modules/error-contracts.md

@@ -0,0 +1,24 @@
+# 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.

.claude/skills/review-pr/references/modules/execution-platforms.md

@@ -0,0 +1,23 @@
+# 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.

.claude/skills/review-pr/references/modules/input-output-modality.md

@@ -0,0 +1,23 @@
+# 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.

.claude/skills/review-pr/references/modules/model-integration.md

@@ -0,0 +1,25 @@
+# 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.

.claude/skills/review-pr/references/modules/observability.md

@@ -0,0 +1,21 @@
+# 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.

.claude/skills/review-pr/references/modules/omni-connector.md

@@ -0,0 +1,24 @@
+# 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.

.claude/skills/review-pr/references/modules/profiling.md

@@ -0,0 +1,21 @@
+# 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.

.claude/skills/review-pr/references/modules/quantization.md

@@ -0,0 +1,22 @@
+# 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.

.claude/skills/review-pr/references/modules/stage-runtime.md

@@ -0,0 +1,23 @@
+# 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.

.claude/skills/review-pr/references/process/design-contracts.md

@@ -0,0 +1,34 @@
+# 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.

.claude/skills/review-pr/references/process/general-checks.md

@@ -0,0 +1,129 @@
+# 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.

.claude/skills/review-pr/references/process/review-execution.md

@@ -0,0 +1,191 @@
+# 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.

.claude/skills/review-pr/references/process/review-routing.md

@@ -0,0 +1,76 @@
+# 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.

.github/CODEOWNERS

@@ -1,6 +1,11 @@
 # CODEOWNERS is used to automatically assign PR reviewers
 # Format: path pattern @username or @team
 # More info: https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners
+#
+# The vllm_omni/** source-tree rules below are derived from the `owners` and
+# `primary_code_paths` front matter in docs/design/module/*.md. When updating
+# ownership, update the design doc first, then regenerate the matching rule here.
+# Last-match-wins: more specific rules must come AFTER broader ones.
 
 # Default owners (fallback reviewers for all files)
 * @Gaohan123 @hsliuustc0106 @ywang96
@@ -21,25 +26,10 @@
 # CI
 /.buildkite/ @yenuo26 @congw729 @NickCao
 
-# Engine and model_executor
-/vllm_omni/core/ @tzhouam @yinpeiqi @fake0fan @Sy0307
-/vllm_omni/engine/ @tzhouam @yinpeiqi @fake0fan @Sy0307
-/vllm_omni/entrypoints/ @tzhouam @yinpeiqi @fake0fan @alex-jw-brooks @NickCao
-/vllm_omni/model_executor/ @tzhouam @gcanlin
-/vllm_omni/worker/ @tzhouam @gcanlin
+# ComfyUI / external apps
+/apps/ @fhfuih @alex-jw-brooks
 
-# Diffusion
-/vllm_omni/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @david6666666 @xuechendi
-/vllm_omni/lora/ @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @yuanheng-zhao
-
-# Diffusion CPU offloading
-/vllm_omni/diffusion/offloader/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @yuanheng-zhao @xuechendi
-
-# Omni and TTS support
-/vllm_omni/transformers_utils/ @tzhouam @yuanheng-zhao
-/vllm_omni/model_executor/models/ @linyueqian @ZeldaHuang @princepride @yuanheng-zhao @amy-why-3459 @Bounty-hunter @Sy0307 @gcanlin @NickCao
-
-# Benchmarks
+# Benchmarks (out-of-tree)
 /benchmarks/accuracy/ @david6666666
 /benchmarks/build_dataset/ @linyueqian @yuanheng-zhao
 /benchmarks/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @xuechendi
@@ -47,20 +37,112 @@
 /benchmarks/glm_image/ @princepride @JaredforReal
 /benchmarks/tts/ @linyueqian @ZeldaHuang @princepride @Sy0307 @gcanlin
 
-# Usability and Observability
-/vllm_omni/deploy/ @tzhouam @lishunyang12
-/vllm_omni/metrics/ @lishunyang12
-/vllm_omni/profiler/ @gcanlin
+# =====================================================================
+# Module design ownership (docs/design/module/*.md)
+# Each section header cites the source design doc.
+# =====================================================================
 
-# ComfyUI
-/apps/ @fhfuih @alex-jw-brooks
+# Autoregressive runtime — docs/design/module/ar_runtime.md
+/vllm_omni/core/ @tzhouam @yinpeiqi @fake0fan @Sy0307 @Gaohan123
+/vllm_omni/worker/ @tzhouam @yinpeiqi @fake0fan @Sy0307 @Gaohan123
 
-# Large Scale Serving
+# Engine orchestration & stage runtime — docs/design/module/engine_orchestration.md, stage_runtime.md
+/vllm_omni/engine/ @tzhouam @fake0fan
+# File-level overrides: input/output modality contracts own these engine files
+# — docs/design/module/input_output_modality_contracts.md
+/vllm_omni/engine/messages.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/serialization.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/mm_outputs.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/output_modality.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/output_processor.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+
+# Input/output modality contracts — docs/design/module/input_output_modality_contracts.md
+/vllm_omni/inputs/ @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/outputs/ @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/request.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/data_entry_keys.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+
+# Entrypoints and serving boundaries — docs/design/module/entrypoints.md
+/vllm_omni/entrypoints/ @alex-jw-brooks @linyueqian @NickCao
+# File-level overrides within entrypoints/
+/vllm_omni/entrypoints/openai/errors.py @alex-jw-brooks @NickCao
+/vllm_omni/entrypoints/cli/benchmark/ @alex-jw-brooks @Bounty-hunter
+
+# Error contracts — docs/design/module/error_contracts.md
+/vllm_omni/errors.py @alex-jw-brooks @NickCao
+
+# OmniConnector (inter-stage transport) — docs/design/module/omni_connector.md
 /vllm_omni/distributed/ @princepride @yuanheng-zhao @xuechendi @natureofnature @fake0fan
 
-# Quantization and configuration
+# Model integration — docs/design/module/model_integration.md
+/vllm_omni/model_executor/ @tzhouam @gcanlin
+/vllm_omni/model_executor/models/ @tzhouam @gcanlin @Sy0307 @amy-why-3459 @linyueqian
+/vllm_omni/model_extras/ @tzhouam @gcanlin @princepride
+/vllm_omni/plugins/ @gcanlin @tjtanaa @xuechendi
+# Config override within model_executor — docs/design/module/vllm_omni_config.md
+/vllm_omni/model_executor/stage_configs/ @lishunyang12 @alex-jw-brooks
+
+# Execution platforms (hardware backends) — docs/design/module/execution_platforms.md
+/vllm_omni/platforms/ @gcanlin @tjtanaa @xuechendi
+/vllm_omni/attention/ @gcanlin @tjtanaa @xuechendi @david6666666 @lishunyang12
+
+# Configuration & deploy — docs/design/module/vllm_omni_config.md
 /vllm_omni/config/ @lishunyang12 @alex-jw-brooks
+/vllm_omni/deploy/ @lishunyang12 @alex-jw-brooks
+
+# Quantization — docs/design/module/quantization.md
 /vllm_omni/quantization/ @david6666666 @Isotr0py @lishunyang12
 
-# Hardware plugins and accelerators
-/vllm_omni/platforms/ @gcanlin @tjtanaa @xuechendi
+# Observability — docs/design/module/observability.md
+/vllm_omni/metrics/ @lishunyang12 @vraiti
+
+# Profiling — docs/design/module/profiling.md
+/vllm_omni/profiler/ @gcanlin
+
+# Benchmarking (in-tree) — docs/design/module/benchmarking.md
+/vllm_omni/benchmarks/ @alex-jw-brooks @Bounty-hunter
+
+# LoRA (no dedicated design doc; ownership intentionally narrowed)
+/vllm_omni/lora/ @SamitHuang @wtomin
+
+# Transformers utils (related path only in design docs; preserves prior ownership)
+/vllm_omni/transformers_utils/ @tzhouam @yuanheng-zhao
+
+# =====================================================================
+# Diffusion module family — docs/design/module/diffusion/
+# Umbrella rule first; sub-module rules after it win via last-match.
+# =====================================================================
+
+# Diffusion umbrella (top-level files: data.py, forward_context.py, etc.)
+# — docs/design/module/diffusion/index.md
+/vllm_omni/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @david6666666 @xuechendi
+
+# Cache management — docs/design/module/cache_management.md
+/vllm_omni/diffusion/cache/ @Isotr0py @princepride @SamitHuang
+
+# Diffusion quantization — docs/design/module/quantization.md
+/vllm_omni/diffusion/quantization/ @david6666666 @Isotr0py @lishunyang12
+
+# Diffusion profiling — docs/design/module/profiling.md
+/vllm_omni/diffusion/profiler/ @gcanlin
+
+# Diffusion runtime (scheduler, executor, worker)
+# — docs/design/module/diffusion/diffusion_runtime.md, continuous_batching.md
+/vllm_omni/diffusion/sched/ @Isotr0py @princepride @SamitHuang @fhfuih
+/vllm_omni/diffusion/executor/ @Isotr0py @princepride @SamitHuang @fhfuih
+/vllm_omni/diffusion/worker/ @Isotr0py @princepride @SamitHuang @fhfuih
+
+# Diffusion model integration (pipelines, registration, checkpoint loading)
+# — docs/design/module/diffusion/diffusion_model_integration.md
+/vllm_omni/diffusion/models/ @fhfuih @Bounty-hunter @wtomin
+/vllm_omni/diffusion/model_loader/ @fhfuih @Bounty-hunter @wtomin @RuixiangMa
+/vllm_omni/diffusion/lora/ @fhfuih @Bounty-hunter @wtomin @RuixiangMa
+
+# Diffusion parallelism (rank topology, TP/SP/PP/VAE patch)
+# — docs/design/module/diffusion/parallelism.md
+/vllm_omni/diffusion/distributed/ @princepride @yuanheng-zhao @xuechendi @Bounty-hunter
+/vllm_omni/diffusion/attention/parallel/ @princepride @yuanheng-zhao @xuechendi @Bounty-hunter
+
+# Diffusion offloader (CPU offloading, DLO)
+# — docs/design/module/diffusion/offloader.md
+/vllm_omni/diffusion/offloader/ @yuanheng-zhao @david6666666 @lishunyang12

.pre-commit-config.yaml

@@ -61,6 +61,16 @@ 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)|tools/pre_commit/check_tts_adapter\.py)$
+      # The budget-is-now-slack reminder is printed on a PASSING run, and
+      # pre-commit hides output from passing hooks unless the hook is verbose.
+      verbose: true
+
     # Keep `suggestion` last
     - id: suggestion
       name: Suggestion

README.md

@@ -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/111-L8zF7A1j_YI_cR8JsblofdScdRr2f/edit?usp=sharing&ouid=110473603432222024453&rtpof=true&sd=true"><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/1aPj0OGl_-ZVoib-Qne5dGDAlrRFB-PdHl6E-EE99g8E/edit?usp=sharing"><b>Slides</b></a> |
 </p>
 
 

docs/.nav.yml

@@ -16,31 +16,21 @@ nav:
   - Examples:
     - examples/README.md
     - Offline Inference:
-      - GLM-Image Multistage End-to-End Inference: user_guide/examples/offline_inference/glm_image.md
-      - HunyuanImage-3.0 Image-to-Text Inference: user_guide/examples/offline_inference/hunyuan_image3.md
       - Image-To-Image: user_guide/examples/offline_inference/image_to_image.md
       - Image-To-Video: user_guide/examples/offline_inference/image_to_video.md
-      - InternVLA-A1: user_guide/examples/offline_inference/internvla_a1.md
-      - MiMo-Audio: user_guide/examples/offline_inference/mimo_audio.md
-      - Qwen2.5-Omni: user_guide/examples/offline_inference/qwen2_5_omni.md
-      - Qwen3-Omni: user_guide/examples/offline_inference/qwen3_omni.md
+      - Speech-To-Video: user_guide/examples/offline_inference/speech_to_video.md
       - Text-To-Audio: user_guide/examples/offline_inference/text_to_audio.md
       - Text-To-Image: user_guide/examples/offline_inference/text_to_image.md
       - Text-To-Speech: user_guide/examples/offline_inference/text_to_speech.md
       - Text-To-Video: user_guide/examples/offline_inference/text_to_video.md
+      - X-To-Text: user_guide/examples/offline_inference/x_to_text.md
       - X-To-Video-Audio: user_guide/examples/offline_inference/x_to_video_audio.md
     - Online Serving:
-      - BAGEL-7B-MoT: user_guide/examples/online_serving/bagel.md
-      - vLLM-Omni Helm Chart: user_guide/examples/online_serving/chart-helm.md
-      - Diffusers Backend Adapter: user_guide/examples/online_serving/diffusers_pipeline_adapter.md
-      - GLM-Image Online Serving: user_guide/examples/online_serving/glm_image.md
       - Image-To-Image: user_guide/examples/online_serving/image_to_image.md
       - Image-To-Video: user_guide/examples/online_serving/image_to_video.md
-      - MiMo-Audio: user_guide/examples/online_serving/mimo_audio.md
-      - Qwen2.5-Omni: user_guide/examples/online_serving/qwen2_5_omni.md
-      - Qwen3-Omni: user_guide/examples/online_serving/qwen3_omni.md
-      - Text-To-Speech: user_guide/examples/online_serving/text_to_speech.md
+      - Speech-To-Video: user_guide/examples/online_serving/speech_to_video.md
       - Text-To-Image: user_guide/examples/online_serving/text_to_image.md
+      - Text-To-Speech: user_guide/examples/online_serving/text_to_speech.md
       - Text-To-Video: user_guide/examples/online_serving/text_to_video.md
   - General:
     - usage/*
@@ -138,12 +128,28 @@ nav:
       - Prometheus Metrics: design/metrics.md
       - Speech Generation Performance Optimizations: design/qwen3_omni_tts_performance_optimization.md
     - Module Design:
-      - Runtime Modules:
-        - AR Module: design/module/ar_module.md
-        - DIT Module: design/module/dit_module.md
-      - Orchestration:
-        - Entrypoint Module: design/module/entrypoint_module.md
-        - AsyncOmni Architecture: design/module/async_omni_architecture.md
+      - Entrypoints: design/module/entrypoints.md
+      - vLLM-Omni Configuration: design/module/vllm_omni_config.md
+      - Input, Output, and Modality Contracts: design/module/input_output_modality_contracts.md
+      - Error Contracts: design/module/error_contracts.md
+      - Engine Orchestration: design/module/engine_orchestration.md
+      - Stage Runtime: design/module/stage_runtime.md
+      - OmniConnector: design/module/omni_connector.md
+      - Model Integration: design/module/model_integration.md
+      - Autoregressive Runtime: design/module/ar_runtime.md
+      - Diffusion:
+        - Overview: design/module/diffusion/index.md
+        - Runtime: design/module/diffusion/diffusion_runtime.md
+        - Model Integration: design/module/diffusion/diffusion_model_integration.md
+        - Continuous Batching: design/module/diffusion/continuous_batching.md
+        - Parallelism: design/module/diffusion/parallelism.md
+        - Offloader: design/module/diffusion/offloader.md
+      - Execution Platforms: design/module/execution_platforms.md
+      - Cache Management: design/module/cache_management.md
+      - Quantization: design/module/quantization.md
+      - Observability: design/module/observability.md
+      - Profiling: design/module/profiling.md
+      - Benchmarking: design/module/benchmarking.md
   - Docs Guide: contributing/DOCS_GUIDE.md
 - API Reference:
   - api/README.md

docs/README.md

@@ -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/1XJWgv79lORl8rbaVvp2d5Sqs6ZEBgAgj/edit?slide=id.p1#slide=id.p1)
+- [vllm-omni architecture design and recent roadmaps](https://docs.google.com/presentation/d/1aPj0OGl_-ZVoib-Qne5dGDAlrRFB-PdHl6E-EE99g8E/edit?usp=sharing)
 - [vllm-omni announcement blogpost](https://blog.vllm.ai/2025/11/30/vllm-omni.html)

docs/contributing/model/adding_tts_model.md

@@ -672,100 +672,147 @@ 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, 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.
+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.
 
-### 1. Stage constant
+### 1. Write the adapter
 
-Near the top of the file, alongside the other `_*_TTS_MODEL_STAGES` constants:
+Create `vllm_omni/entrypoints/openai/tts_adapters/your_model.py`:
 
 ```python
-_YOUR_MODEL_TTS_MODEL_STAGES = {"your_model_stage_key"}
+# 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,
+        )
 ```
 
-### 2. Union into `_TTS_MODEL_STAGES`
+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.
 
-Add to the `_TTS_MODEL_STAGES` set union:
+> **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:
 
 ```python
-_TTS_MODEL_STAGES: set[str] = (
-    ...
-    | _YOUR_MODEL_TTS_MODEL_STAGES
-)
+# 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
 ```
 
-### 3. Model type detection
-
-In `_detect_tts_model_type()`, add before the final `return None`:
+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:
 
 ```python
-if model_stage in _YOUR_MODEL_TTS_MODEL_STAGES:
-    return "your_model"
+@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
 ```
 
-### 4. Request validation dispatch
+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.
 
-In `_validate_tts_request()`, add before the fallback `return`:
+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.
 
-```python
-if self._tts_model_type == "your_model":
-    return self._validate_your_model_request(request)
-```
+### 3. Reuse the shared helpers
 
-### 5. Validation and parameter-builder methods
+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.
 
-Add two new methods:
+### 4. Test it
 
-```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
+`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.
 
-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
-```
+### Do not add branches to `serving_speech.py`
 
-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.
+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.
 
-> **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.
+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.
 
 ### Merge conflicts
 
-`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:
+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:
 
 ```bash
-git add vllm_omni/entrypoints/openai/serving_speech.py
+git add vllm_omni/entrypoints/openai/tts_adapters/__init__.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

docs/design/architecture_overview.md

@@ -1,6 +1,6 @@
 # Architecture Overview
 
-This document outlines the architectural design for vLLM-Omni.
+This document outlines the architecture of vLLM-Omni.
 
 <p align="center">
   <picture>
@@ -9,194 +9,456 @@ This document outlines the architectural design for vLLM-Omni.
   </picture>
 </p>
 
-# Goals
+## Design goals
 
-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 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.
 
-* **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.
+The architecture is designed to:
 
+* 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.
 
-# Representative omni-modality models
+## Model execution
 
-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:
+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.
 
-**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.
+| 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.
 
 <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/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>
+  <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>
 </p>
 
-**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.
+#### 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.
 
 <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/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>
+  <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>
 </p>
 
-**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...).
+#### 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.
 
 <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/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>
+  <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>
 </p>
 
-# vLLM-Omni main architecture
+#### Model architecture by stage
 
-<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>
+| 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 |
 
-## Key Components
+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.
 
-| 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                    |
+#### Representative stage execution
 
-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`.
+| 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.
 
 ## Main features
 
-vLLM-Omni aims to be fast, flexible, and easy to use with the following 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.
 
-### Performance and Acceleration
+### Runtime and stage execution
 
-The framework achieves high performance through several optimization techniques:
+* **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.
 
-* **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.
+### Communication
 
-### Classifier-Free Guidance (CFG) Companion Flow
+* **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.
 
-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.
+### Diffusion acceleration
 
-### Flexibility and Usability
+* **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.
 
-vLLM-Omni is designed to be flexible and straightforward for users:
+## Interfaces
 
-* **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:
+The public interfaces map onto the same engine and stage boundaries:
 
+```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"]
 ```
-# Create an omni runtime with HF model name.
+
+### Offline inference
+
+The **Omni** class provides a Python interface for offline batched inference:
+
+```python
 from vllm_omni.entrypoints.omni import Omni
 
 omni = Omni(model="Qwen/Qwen3-Omni-30B-A3B-Instruct")
 
-# Example prompts.
-om_inputs = {"prompt": prompt,
-             "multi_modal_data": {
-                 "video": video_frames,
-                 "audio": audio_signal,
-             }}
+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
-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:
+### Online serving
 
-```
+The OpenAI-compatible server uses the same stage configuration and engine
+boundaries:
+
+```bash
 vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
 ```
 
-Users can send requests to the server using curl:
+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.
 
-```
-# 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).
+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.

docs/design/index.md

@@ -1,8 +1,9 @@
 # Design Documents
 
 This section contains design documents and architecture specifications for
-vLLM-Omni. The sidebar groups documents by the system concern they describe,
-while the source paths remain stable so existing links continue to work.
+vLLM-Omni. The sidebar groups documents by the system concern they describe;
+retired module pages are preserved in the legacy archive instead of remaining
+in the active navigation.
 
 ## Architecture Documents
 
@@ -61,12 +62,29 @@ while the source paths remain stable so existing links continue to work.
 
 ## Module Design Documents
 
-### Runtime Modules
+- [Entrypoints and Serving Boundaries](module/entrypoints.md)
+- [vLLM-Omni Configuration](module/vllm_omni_config.md)
+- [Input, Output, and Modality Contracts](module/input_output_modality_contracts.md)
+- [Error Classification, Propagation, and Rendering](module/error_contracts.md)
+- [Engine Orchestration](module/engine_orchestration.md)
+- [Stage Runtime and Replica Lifecycle](module/stage_runtime.md)
+- [OmniConnector](module/omni_connector.md)
+- [Model Integration](module/model_integration.md)
+- [Autoregressive Runtime](module/ar_runtime.md)
+- Diffusion
+  - [Overview](module/diffusion/index.md)
+  - [Runtime](module/diffusion/diffusion_runtime.md)
+  - [Model Integration](module/diffusion/diffusion_model_integration.md)
+  - [Continuous Batching](module/diffusion/continuous_batching.md)
+  - [Parallelism](module/diffusion/parallelism.md)
+  - [Offloader](module/diffusion/offloader.md)
+- [Execution Platforms](module/execution_platforms.md)
+- [Cache Management](module/cache_management.md)
+- [Quantization](module/quantization.md)
+- [Observability](module/observability.md)
+- [Profiling](module/profiling.md)
+- [Benchmarking](module/benchmarking.md)
 
-- [AR Module](module/ar_module.md)
-- [DIT Module](module/dit_module.md)
-
-### Orchestration
-
-- [Entrypoint Module](module/entrypoint_module.md)
-- [AsyncOmni Architecture (Qwen3-Omni Example)](module/async_omni_architecture.md)
+The pre-#5137 pages are preserved in the
+[legacy module archive](module/archive/README.md) for historical reference and
+are not active design contracts.

docs/design/module/ar_runtime.md

@@ -0,0 +1,53 @@
+---
+title: Autoregressive Runtime
+kind: module
+status: draft
+owners:
+  - "@tzhouam"
+  - "@yinpeiqi"
+  - "@fake0fan"
+  - "@Sy0307"
+  - "@Gaohan123"
+primary_code_paths:
+  - vllm_omni/core/**
+  - vllm_omni/worker/**
+related_code_paths:
+  - vllm_omni/model_executor/**
+depends_on:
+  - engine_orchestration.md
+  - model_integration.md
+  - input_output_modality_contracts.md
+validation_paths:
+  - tests/core/**
+  - tests/worker/**
+upstream_refs:
+  - vllm.v1.core
+  - vllm.v1.worker
+last_reviewed: 2026-07-16
+---
+
+# Autoregressive runtime
+
+The AR runtime extends vLLM scheduling and worker execution for omni-stage
+inputs and outputs while preserving vLLM scheduling and cache semantics.
+
+## Candidate invariants
+
+### AR-INV-001: vLLM owns base scheduling semantics
+
+**Rule:** Omni schedulers MUST preserve upstream request-state and cache
+transitions unless an Omni-specific difference is documented and tested.
+
+### AR-INV-002: Omni data crosses explicit adapters
+
+**Rule:** Modality-specific stage data MUST be converted at an input or output
+adapter, not injected through unrelated scheduler state.
+
+### AR-INV-003: Workers execute assigned work
+
+**Rule:** Workers and model runners MUST NOT implement cross-stage routing.
+
+## Safe-change guide
+
+Test request lifecycle, abort, cache state, and every affected worker execution
+mode against the supported upstream vLLM contract.

docs/design/module/archive/README.md

@@ -0,0 +1,18 @@
+# Archived module design pages
+
+This directory preserves module-design pages that predate the structure
+proposed in [issue #5137](https://github.com/vllm-project/vllm-omni/issues/5137).
+They are historical snapshots, not active architectural contracts, and are
+intentionally excluded from the documentation navigation.
+
+| Archived page | Active destination |
+| --- | --- |
+| [AR Module](ar_module.md) | [Autoregressive Runtime](../ar_runtime.md) |
+| [AsyncOmni Architecture](async_omni_architecture.md) | [Engine Orchestration](../engine_orchestration.md) and [Stage Runtime](../stage_runtime.md) |
+| [DiT Module](dit_module.md) | [Diffusion module overview](../diffusion/index.md) |
+| [Entrypoint Module](entrypoint_module.md) | [Entrypoints and Serving Boundaries](../entrypoints.md) |
+
+Do not update these pages with current design guidance. Move still-useful
+material into the active destination and review it against current code and
+tests instead. No compatibility redirect pages are provided at the former
+paths.

docs/design/module/archive/ar_module.md

@@ -12,7 +12,7 @@ The AR module of vLLM-Omni extends vLLM's core components to support:
 - **Hidden state exposure**: Exposing per-request hidden representations for downstream stages
 - **Basic generator support**: Support some basic heterogeneous architecture such as Convolution, LSTM, etc.
 
-As shown in the [end2end example](../../user_guide/examples/offline_inference/qwen3_omni.md), AR module can be widely applied across multiple stages, generating text tokens in thinker(AR), audio latent tokens in talker(AR) and audio wave in code2wav(Convolution).
+As shown in the [end2end example](../../../user_guide/examples/offline_inference/qwen3_omni.md), AR module can be widely applied across multiple stages, generating text tokens in thinker(AR), audio latent tokens in talker(AR) and audio wave in code2wav(Convolution).
 
 ## 2. Relationship with vLLM
 

docs/design/module/archive/dit_module.md

@@ -252,7 +252,7 @@ while True:
   batch of compatible independent requests for one full pipeline forward when
   the pipeline supports request-level batching; the step-wise path can also
   admit or remove compatible requests between denoise steps. See
-  [Diffusion Continuous Batching](../feature/diffusion_continuous_batching.md).
+  [Diffusion Continuous Batching](../../feature/diffusion_continuous_batching.md).
 
 ---
 
@@ -541,7 +541,7 @@ def get_attn_backend_for_role(role, head_size, attention_config=None, role_categ
 
 A backend that needs configuration exposes it as a typed field on `AttentionSpec`; `AttentionSpec.backend_kwargs()` serializes it into the `backend_kwargs` the impl consumes. Today those fields are `skip_softmax` (TRTLLM_ATTN) and `block_sparse` (any block-sparse backend, currently RAINFUSION_ATTN), so e.g. `target_sparsity` or `sparsity` can be set without changing model code.
 
-For the user-facing CLI surface, see [Diffusion Attention Backends](../../user_guide/diffusion/attention_backends.md). For the role declaration contract on the model side, see [Adding a Diffusion Model](../../contributing/model/adding_diffusion_model.md).
+For the user-facing CLI surface, see [Diffusion Attention Backends](../../../user_guide/diffusion/attention_backends.md). For the role declaration contract on the model side, see [Adding a Diffusion Model](../../../contributing/model/adding_diffusion_model.md).
 
 **Backend Availability**:
 

docs/design/module/benchmarking.md

@@ -0,0 +1,48 @@
+---
+title: Benchmarking
+kind: module
+status: draft
+owners:
+  - "@alex-jw-brooks"
+  - "@Bounty-hunter"
+primary_code_paths:
+  - vllm_omni/benchmarks/**
+  - vllm_omni/entrypoints/cli/benchmark/**
+related_code_paths:
+  - benchmarks/**
+depends_on:
+  - entrypoints.md
+  - profiling.md
+validation_paths:
+  - tests/benchmarks/**
+  - tests/dfx/perf/**
+upstream_refs:
+  - vllm.benchmarks
+last_reviewed: 2026-07-16
+---
+
+# Benchmarking
+
+Benchmarking defines reproducible workloads, metrics, warm-up, measurement,
+and result metadata for comparing vLLM-Omni performance.
+
+## Candidate invariants
+
+### BENCH-INV-001: Results are reproducible
+
+**Rule:** Results MUST identify the model, revision, commit, hardware,
+configuration, workload, concurrency, warm-up, and measurement window.
+
+### BENCH-INV-002: Correctness precedes performance
+
+**Rule:** A benchmark MUST validate successful and semantically acceptable
+outputs before using timings as performance evidence.
+
+### BENCH-INV-003: Metric definitions are explicit
+
+**Rule:** Metrics MUST state their unit, population, and aggregation.
+
+## Safe-change guide
+
+Test workload parsing and metric calculations with deterministic fixtures. Do
+not compare materially different workloads or runtime settings.

docs/design/module/cache_management.md

@@ -0,0 +1,48 @@
+---
+title: Cache Management
+kind: module
+status: draft
+owners:
+  - "@Isotr0py"
+  - "@princepride"
+  - "@SamitHuang"
+primary_code_paths:
+  - vllm_omni/diffusion/cache/**
+related_code_paths:
+  - vllm_omni/experimental/ar_diffusion/kv_cache/**
+  - vllm_omni/core/**
+depends_on:
+  - ar_runtime.md
+  - diffusion/diffusion_runtime.md
+validation_paths:
+  - tests/diffusion/cache/**
+upstream_refs:
+  - vllm.v1.core.kv_cache_manager
+last_reviewed: 2026-07-16
+---
+
+# Cache management
+
+Cache management defines reusable state, cache identity, validity, lifecycle,
+and eviction across AR and diffusion execution.
+
+## Candidate invariants
+
+### CACHE-INV-001: Cache identity is complete
+
+**Rule:** A cache key MUST include every input and execution property that can
+change the reused value.
+
+### CACHE-INV-002: Reuse preserves correctness
+
+**Rule:** A cache optimization MUST provide a disabled path and MUST NOT reuse
+state after its validity conditions change.
+
+### CACHE-INV-003: Ownership has an end
+
+**Rule:** Request-scoped and model-scoped cache entries MUST have explicit
+reset, eviction, or teardown behavior.
+
+## Safe-change guide
+
+Test hit, miss, invalidation, disabled, concurrent-request, and teardown paths.

docs/design/module/diffusion/continuous_batching.md

@@ -0,0 +1,51 @@
+---
+title: Diffusion Continuous Batching
+kind: module
+status: draft
+owners:
+  - "@Isotr0py"
+  - "@princepride"
+primary_code_paths:
+  - vllm_omni/diffusion/sched/**
+related_code_paths:
+  - vllm_omni/diffusion/executor/**
+depends_on:
+  - diffusion_runtime.md
+validation_paths:
+  - tests/diffusion/batching/**
+upstream_refs: []
+last_reviewed: 2026-07-16
+---
+
+# Diffusion continuous batching
+
+Continuous batching defines when diffusion requests are compatible, how they
+share an execution step, and how each request advances independently.
+
+## Candidate invariants
+
+### BATCH-INV-001: Compatibility is explicit
+
+**Rule:** Requests MAY share a batch only when all properties required by the
+selected pipeline, scheduler step, shape, precision, and execution features are
+compatible.
+
+### BATCH-INV-002: Per-request state remains isolated
+
+**Rule:** Batch assembly MUST preserve each request's random generator, progress,
+conditioning, outputs, cancellation, and errors.
+
+### BATCH-INV-003: Admission is bounded
+
+**Rule:** Admission MUST respect configured capacity and MUST NOT rely on an
+unbounded waiting or active-request collection.
+
+### BATCH-INV-004: Batch order is not completion order
+
+**Rule:** Output association MUST use stable request identity rather than batch
+position across execution steps.
+
+## Safe-change guide
+
+Test heterogeneous requests, partial completion, cancellation, deterministic
+seeds, capacity limits, and batch sizes of one and many.

docs/design/module/diffusion/diffusion_model_integration.md

@@ -0,0 +1,59 @@
+---
+title: Diffusion Model Integration
+kind: module
+status: draft
+owners:
+  - "@fhfuih"
+  - "@Bounty-hunter"
+  - "@wtomin"
+  - "@RuixiangMa"
+primary_code_paths:
+  - vllm_omni/diffusion/models/**
+  - vllm_omni/diffusion/model_loader/**
+related_code_paths:
+  - vllm_omni/diffusion/layers/**
+  - vllm_omni/diffusion/lora/**
+  - vllm_omni/diffusion/utils/**
+depends_on:
+  - diffusion_runtime.md
+  - ../input_output_modality_contracts.md
+validation_paths:
+  - tests/diffusion/models/**
+  - tests/diffusion/model_loader/**
+  - tests/diffusion/layers/**
+  - tests/diffusion/lora/**
+upstream_refs:
+  - diffusers.DiffusionPipeline
+last_reviewed: 2026-07-16
+---
+
+# Diffusion model integration
+
+Diffusion model integration owns pipeline contracts, registration, checkpoint
+loading, adapters, shared layers, and model-specific processing.
+
+## Candidate invariants
+
+### DIFF-MODEL-INV-001: Pipelines implement one runtime contract
+
+**Rule:** A pipeline MUST declare its supported modalities, configuration,
+inputs, outputs, loading path, and runtime capabilities.
+
+### DIFF-MODEL-INV-002: Registration is the selection boundary
+
+**Rule:** Runtime code MUST select model implementations through the registry or
+loader contract rather than scattered model-name conditionals.
+
+### DIFF-MODEL-INV-003: Model code does not schedule requests
+
+**Rule:** Pipeline code MUST NOT own admission, batching, cancellation, or
+cross-stage routing.
+
+### DIFF-MODEL-INV-004: Shared behavior stays shared
+
+**Rule:** Model directories SHOULD contain only genuine model differences.
+
+## Safe-change guide
+
+Test registry selection, checkpoint loading, minimal inference, input and output
+contracts, and every declared optional capability.

docs/design/module/diffusion/diffusion_runtime.md

@@ -0,0 +1,59 @@
+---
+title: Diffusion Runtime
+kind: module
+status: draft
+owners:
+  - "@Isotr0py"
+  - "@princepride"
+  - "@SamitHuang"
+  - "@fhfuih"
+primary_code_paths:
+  - vllm_omni/diffusion/sched/**
+  - vllm_omni/diffusion/executor/**
+  - vllm_omni/diffusion/worker/**
+related_code_paths:
+  - vllm_omni/diffusion/hooks/**
+  - vllm_omni/diffusion/postprocess/**
+depends_on:
+  - ../engine_orchestration.md
+  - ../input_output_modality_contracts.md
+  - diffusion_model_integration.md
+validation_paths:
+  - tests/diffusion/diffusion_backend/**
+  - tests/diffusion/hooks/**
+upstream_refs:
+  - diffusers.DiffusionPipeline
+last_reviewed: 2026-07-16
+---
+
+# Diffusion runtime
+
+The diffusion runtime owns request admission, scheduling, execution, progress,
+output, cancellation, and cleanup inside a diffusion stage.
+
+## Candidate invariants
+
+### DIFF-RUNTIME-INV-001: One lifecycle owner
+
+**Rule:** Every admitted request MUST have exactly one scheduler-owned lifecycle
+until completion, cancellation, or failure.
+
+### DIFF-RUNTIME-INV-002: Execution follows scheduler output
+
+**Rule:** Executors and workers MUST execute scheduler decisions without
+admitting, reordering, or forwarding requests independently.
+
+### DIFF-RUNTIME-INV-003: Terminal cleanup is complete
+
+**Rule:** Every terminal path MUST release request state, temporary tensors,
+hooks, and runtime-owned resources.
+
+### DIFF-RUNTIME-INV-004: Optional features use runtime hooks
+
+**Rule:** Cache, profiling, offload, and parallel features SHOULD integrate at
+defined hooks instead of creating another request lifecycle.
+
+## Safe-change guide
+
+Test success, cancellation, failure, shutdown, multiple requests, and resource
+cleanup.

docs/design/module/diffusion/index.md

@@ -0,0 +1,42 @@
+---
+title: Diffusion Modules
+kind: module-index
+status: draft
+owners:
+  - "@Isotr0py"
+  - "@princepride"
+  - "@SamitHuang"
+  - "@wtomin"
+  - "@ZJY0516"
+  - "@RuixiangMa"
+  - "@david6666666"
+  - "@xuechendi"
+primary_code_paths:
+  - vllm_omni/diffusion/**
+related_code_paths:
+  - vllm_omni/platforms/**
+depends_on:
+  - ../engine_orchestration.md
+  - ../input_output_modality_contracts.md
+validation_paths:
+  - tests/diffusion/**
+upstream_refs:
+  - diffusers
+last_reviewed: 2026-07-16
+---
+
+# Diffusion modules
+
+Diffusion is a module family containing runtime, model integration, batching,
+distributed execution, and memory-management subsystems.
+
+## Module documents
+
+- [Diffusion runtime](diffusion_runtime.md)
+- [Diffusion model integration](diffusion_model_integration.md)
+- [Continuous batching](continuous_batching.md)
+- [Parallelism](parallelism.md)
+- [Offloader](offloader.md)
+
+Cache, quantization, profiling, and benchmarking follow their top-level module
+documents.

docs/design/module/diffusion/offloader.md

@@ -0,0 +1,54 @@
+---
+title: Diffusion Offloader
+kind: module
+status: draft
+owners:
+  - "@yuanheng-zhao"
+  - "@david6666666"
+  - "@lishunyang12"
+primary_code_paths:
+  - vllm_omni/diffusion/offloader/**
+related_code_paths:
+  - vllm_omni/diffusion/models/**
+  - vllm_omni/diffusion/worker/**
+depends_on:
+  - diffusion_runtime.md
+  - ../execution_platforms.md
+validation_paths:
+  - tests/diffusion/offloader/**
+upstream_refs:
+  - torch.nn.Module.to
+last_reviewed: 2026-07-16
+---
+
+# Diffusion offloader
+
+The offloader owns component residency, transfer scheduling, memory accounting,
+prefetch, and teardown for diffusion execution.
+
+## Candidate invariants
+
+### OFFLOAD-INV-001: Residency is explicit
+
+**Rule:** Each managed component MUST have one known residency state and one
+owner responsible for transitions.
+
+### OFFLOAD-INV-002: Use follows readiness
+
+**Rule:** Runtime execution MUST NOT consume a component until its transfer to
+the required device is complete.
+
+### OFFLOAD-INV-003: Transfers preserve model state
+
+**Rule:** Offloading MUST preserve parameter and buffer identity, dtype, device,
+and correctness required by the selected execution mode.
+
+### OFFLOAD-INV-004: Memory is bounded and released
+
+**Rule:** Retained host and device copies MUST respect configured limits and
+provide deterministic teardown.
+
+## Safe-change guide
+
+Test enabled and disabled paths, repeated execution, asynchronous transfer,
+memory limits, failure, teardown, and numerical equivalence.

docs/design/module/diffusion/parallelism.md

@@ -0,0 +1,57 @@
+---
+title: Diffusion Parallelism
+kind: module
+status: draft
+owners:
+  - "@princepride"
+  - "@yuanheng-zhao"
+  - "@xuechendi"
+  - "@Bounty-hunter"
+primary_code_paths:
+  - vllm_omni/diffusion/distributed/**
+  - vllm_omni/diffusion/attention/parallel/**
+related_code_paths:
+  - vllm_omni/distributed/**
+  - vllm_omni/config/composable_parallel/**
+depends_on:
+  - diffusion_runtime.md
+  - ../vllm_omni_config.md
+validation_paths:
+  - tests/diffusion/distributed/**
+  - tests/diffusion/attention/**
+upstream_refs:
+  - torch.distributed
+last_reviewed: 2026-07-16
+---
+
+# Diffusion parallelism
+
+Parallelism owns diffusion rank topology, process groups, tensor and sequence
+sharding, collectives, and distributed execution.
+
+## Candidate invariants
+
+### PARALLEL-INV-001: Topology has one source of truth
+
+**Rule:** Rank coordinates, group membership, and parallel dimensions MUST be
+derived from validated configuration.
+
+### PARALLEL-INV-002: Sharding contracts are explicit
+
+**Rule:** Every distributed boundary MUST define tensor shape, sharded
+dimension, placement, dtype, producer, and consumer.
+
+### PARALLEL-INV-003: Collectives are symmetric
+
+**Rule:** Process-group members MUST invoke compatible collectives in the same
+logical order.
+
+### PARALLEL-INV-004: Single-rank behavior remains valid
+
+**Rule:** Distributed implementations SHOULD preserve a supported single-rank
+path without distributed initialization.
+
+## Safe-change guide
+
+Test topology validation, single-rank execution, affected parallel modes,
+combined modes, invalid shapes, and orderly teardown.

docs/design/module/engine_orchestration.md

@@ -0,0 +1,122 @@
+---
+title: Engine Orchestration
+kind: module
+status: draft
+architecture_state: current-plus-in-flight
+owners:
+  - "@tzhouam"
+  - "@fake0fan"
+document_stewards:
+  - "@hsliuustc0106"
+  - "@Gaohan123"
+  - "@david6666666"
+required_reviewers:
+  - "@yinpeiqi"
+  - "@Sy0307"
+  - "@yenuo26"
+  - "@NickCao"
+primary_code_paths:
+  - vllm_omni/engine/async_omni_engine.py
+  - vllm_omni/engine/async_engine_utils.py
+  - vllm_omni/engine/orchestrator.py
+  - vllm_omni/engine/cfg_companion_tracker.py
+  - vllm_omni/engine/rpc_result_router.py
+related_code_paths:
+  - vllm_omni/engine/messages.py
+  - vllm_omni/engine/orchestrator_monitor.py
+  - vllm_omni/engine/stage_client.py
+  - vllm_omni/engine/stage_pool.py
+  - vllm_omni/outputs/output_processor.py
+  - vllm_omni/distributed/omni_coordinator/**
+depends_on:
+  - input_output_modality_contracts.md
+  - error_contracts.md
+  - stage_runtime.md
+  - omni_connector.md
+validation_paths:
+  - tests/engine/test_async_omni_engine_input.py
+  - tests/engine/test_async_omni_engine_outputs.py
+  - tests/engine/test_async_omni_engine_abort.py
+  - tests/engine/test_async_omni_engine_stage_init.py
+  - tests/engine/test_orchestrator.py
+  - tests/engine/test_orchestrator_error_handling.py
+  - tests/engine/test_orchestrator_stage_input_bridge.py
+  - tests/engine/test_cfg_companion_lifecycle.py
+  - tests/engine/test_rpc_result_router.py
+  - tests/e2e/features/fullduplex/engine/**
+upstream_refs:
+  - vllm.v1.engine.EngineCoreRequest
+  - vllm.v1.engine.EngineCoreOutputs
+  - vllm.v1.engine.exceptions.EngineDeadError
+  - vllm.outputs.RequestOutput
+invariant_namespace: ORCH-INV
+last_reviewed: 2026-08-07
+last_verified_commit: 3d7fc3b9ba3cac88d579d4dc35b78b0b641675fc
+---
+
+# Engine orchestration
+
+Engine orchestration coordinates configured AR and diffusion stages while
+keeping public clients independent from stage processes and transports.
+
+## Contract status
+
+This document is a draft description of current behavior. It also identifies
+the boundary affected by the in-flight stage client/process refactor in
+[#5441](https://github.com/vllm-project/vllm-omni/pull/5441). Names and
+responsibilities proposed only by that PR are not current contracts.
+
+## Ownership boundary
+
+This document owns `AsyncOmniEngine`, `Orchestrator`, request-state creation,
+cross-stage routing, output ordering, companion tracking, control/RPC
+correlation, cancellation propagation, and terminal-state convergence.
+
+It does not own stage placement, replica selection, stage-process startup,
+payload schemas, public protocol rendering, connector transport, or semantic
+error classification. Those responsibilities belong to the stage runtime,
+I/O, entrypoint, connector, and error contracts.
+
+## Candidate invariants
+
+These identifiers are proposals while the document is `draft`.
+
+### ORCH-INV-001: The orchestrator owns cross-stage routing
+
+**Rule:** Entrypoints and stage clients MUST NOT independently forward a
+request to a downstream logical stage.
+
+### ORCH-INV-002: Stage clients do not own routing policy
+
+**Rule:** Stage clients MUST implement communication and lifecycle operations
+without selecting the next logical stage.
+
+### ORCH-INV-100: Terminal state is monotonic
+
+**Rule:** Once a request reaches a terminal state, orchestration MUST NOT
+forward new work for that request.
+
+## Invariant namespace
+
+`ORCH-INV` reserves `001-099` for dependency direction, `100-199` for
+request state and ordering, `200-299` for failure/cancellation/cleanup, and
+`300-399` for extension points, shutdown ordering, and upstream alignment.
+Numbers become append-only after normative promotion.
+
+## Safe-change guide
+
+Test routing, output ordering, queue correlation, cancellation, failure
+propagation, shutdown ordering, and representative multi-stage execution.
+Changes that cross into stage runtime or public error behavior require review
+from that contract's owners.
+
+## Promotion gate
+
+- Reconcile current names and boundaries after #5441 merges, closes, or is
+  replaced.
+- Demonstrate one terminal outcome per request across success, abort,
+  request-scoped failure, and fatal engine failure.
+- Verify queue correlation and orchestrator-before-runtime shutdown ordering
+  in the cited validation paths.
+- Obtain approval from a technical owner and an independent validation
+  reviewer.

docs/design/module/entrypoints.md

@@ -0,0 +1,135 @@
+---
+title: Entrypoints and Serving Boundaries
+kind: module
+status: draft
+architecture_state: current-plus-in-flight
+owners:
+  - "@alex-jw-brooks"
+  - "@linyueqian"
+  - "@NickCao"
+document_stewards:
+  - "@hsliuustc0106"
+  - "@Gaohan123"
+  - "@david6666666"
+required_reviewers:
+  - "@tzhouam"
+  - "@herotai214"
+  - "@yenuo26"
+  - "@NickCao"
+primary_code_paths:
+  - vllm_omni/entrypoints/omni.py
+  - vllm_omni/entrypoints/async_omni.py
+  - vllm_omni/entrypoints/omni_base.py
+  - vllm_omni/entrypoints/cli/**
+  - vllm_omni/entrypoints/openai/**
+  - vllm_omni/entrypoints/openpi/**
+  - vllm_omni/entrypoints/client_request_state.py
+  - vllm_omni/entrypoints/stage_utils.py
+  - vllm_omni/entrypoints/utils.py
+primary_path_exceptions:
+  - path: vllm_omni/entrypoints/openai/errors.py
+    owner: error_contracts.md
+related_code_paths:
+  - vllm_omni/errors.py
+  - vllm_omni/inputs/**
+  - vllm_omni/outputs/**
+  - vllm_omni/engine/async_omni_engine.py
+  - vllm_omni/config/**
+  - vllm_omni/deploy/**
+depends_on:
+  - input_output_modality_contracts.md
+  - error_contracts.md
+  - engine_orchestration.md
+validation_paths:
+  - tests/entrypoints/test_omni_entrypoints.py
+  - tests/entrypoints/test_async_omni.py
+  - tests/entrypoints/test_async_omni_duplex.py
+  - tests/entrypoints/test_serve.py
+  - tests/entrypoints/test_stream_finish_reason.py
+  - tests/entrypoints/openai/**
+  - tests/entrypoints/openai_api/**
+  - tests/e2e/online_serving/**
+upstream_refs:
+  - vllm.engine.protocol.EngineClient
+  - vllm.entrypoints.openai/**
+  - vllm.entrypoints.serve/**
+  - vllm.renderers/**
+  - vllm.v1.engine.exceptions/**
+invariant_namespace: ENTRY-INV
+last_reviewed: 2026-08-07
+last_verified_commit: 3d7fc3b9ba3cac88d579d4dc35b78b0b641675fc
+---
+
+# Entrypoints and serving boundaries
+
+Entrypoints translate offline, CLI, and serving requests into stable engine
+operations and translate engine outputs into public responses.
+
+## Contract status
+
+This document describes current entrypoint responsibilities plus the boundary
+under review in the open roadmap
+[#5227](https://github.com/vllm-project/vllm-omni/issues/5227) and helper-move
+PR [#5453](https://github.com/vllm-project/vllm-omni/pull/5453). In-flight
+helper locations are not treated as current paths.
+
+## Ownership boundary
+
+This document owns offline API semantics, CLI and serve composition,
+supported OpenAI-compatible routes, request validation and normalization,
+response conversion, streaming/session behavior, and engine handoff.
+
+It does not own configuration precedence, cross-stage routing, stage
+placement, payload implementation, or semantic error classification.
+`entrypoints/openai/errors.py` is an explicit primary-path exception owned by
+`error_contracts.md`.
+
+## Candidate invariants
+
+These identifiers are proposals while the document is `draft`.
+
+### ENTRY-INV-001: Entrypoints adapt but do not orchestrate
+
+**Rule:** Entrypoints MUST NOT implement cross-stage routing or stage lifecycle
+policy.
+
+### ENTRY-INV-100: Public requests are normalized once
+
+**Rule:** Public protocol values MUST be validated and converted to internal
+request contracts before engine submission.
+
+### ENTRY-INV-101: Streaming preserves request identity
+
+**Rule:** Every streamed response MUST remain associated with the request and
+output modality that produced it.
+
+The reviewer-proposed rule that model-specific behavior should stay behind a
+common adapter or processor abstraction remains an unnumbered candidate until
+the entrypoint refactor makes that boundary enforceable.
+
+## Invariant namespace
+
+`ENTRY-INV` reserves `001-099` for boundary and dependency direction,
+`100-199` for normalization, sessions, and streaming, `200-299` for
+disconnect, cancellation, rendering, and cleanup, and `300-399` for upstream
+route and renderer compatibility. Numbers become append-only after normative
+promotion.
+
+## Safe-change guide
+
+Test request validation, protocol conversion, model-adapter routing,
+streaming, session identity, disconnect/cancellation, and error mapping for
+each affected offline or serving entrypoint.
+
+## Promotion gate
+
+- Reconcile the page after #5227's P0 ownership work and #5453's final
+  disposition.
+- Publish a supported route/transport matrix rather than claiming blanket
+  OpenAI parity.
+- Verify one normalization and handoff path per route family and one terminal
+  outcome per streaming transport.
+- Promote the `api_server.py` composition-root rule only after helper moves and
+  import boundaries enforce it.
+- Obtain approval from a technical owner and an independent validation
+  reviewer.

docs/design/module/error_contracts.md

@@ -0,0 +1,109 @@
+---
+title: Error Classification, Propagation, and Rendering
+kind: module
+status: draft
+architecture_state: current-plus-rfc
+owners:
+  - "@alex-jw-brooks"
+  - "@NickCao"
+document_stewards:
+  - "@hsliuustc0106"
+  - "@Gaohan123"
+  - "@david6666666"
+required_reviewers:
+  - "@yinpeiqi"
+  - "@tzhouam"
+  - "@yenuo26"
+primary_code_paths:
+  - vllm_omni/errors.py
+  - vllm_omni/entrypoints/openai/errors.py
+related_code_paths:
+  - vllm_omni/engine/messages.py
+  - vllm_omni/engine/orchestrator.py
+  - vllm_omni/entrypoints/omni_base.py
+  - vllm_omni/entrypoints/async_omni.py
+  - vllm_omni/entrypoints/openai/api_server.py
+  - vllm_omni/entrypoints/openai/serving_chat.py
+  - vllm_omni/entrypoints/openai/serving_speech.py
+  - vllm_omni/entrypoints/openai/serving_audio_generate.py
+  - vllm_omni/entrypoints/openai/protocol/images.py
+  - vllm_omni/entrypoints/openai/protocol/videos.py
+depends_on: []
+validation_paths:
+  - tests/engine/test_orchestrator_error_handling.py
+  - tests/engine/test_async_omni_engine_outputs.py
+  - tests/entrypoints/test_omni_entrypoints.py
+  - tests/entrypoints/test_stream_finish_reason.py
+  - tests/entrypoints/openai_api/test_image_server.py
+  - tests/entrypoints/openai_api/test_video_server.py
+  - tests/entrypoints/openai_api/test_serving_audio_generate.py
+  - tests/entrypoints/openai_api/test_serving_speech.py
+  - tests/metrics/test_prometheus.py
+upstream_refs:
+  - vllm.v1.engine.exceptions.EngineDeadError
+  - vllm.v1.engine.exceptions.EngineGenerateError
+  - vllm.entrypoints.serve.utils.error_response
+  - vLLM RFC #48227
+  - vLLM PR #49665
+invariant_namespace: ERR-INV
+last_reviewed: 2026-08-07
+last_verified_commit: 3d7fc3b9ba3cac88d579d4dc35b78b0b641675fc
+---
+
+# Error classification, propagation, and rendering
+
+This contract separates the meaning of a failure from the transport used to
+carry it and the public protocol used to render it.
+
+## Contract status
+
+Current behavior is distributed across engine, message, and entrypoint code.
+The semantic hierarchy proposed by
+[#5570](https://github.com/vllm-project/vllm-omni/issues/5570) remains an open
+RFC. Proposed types and wire records from that RFC are not current contracts.
+
+## Ownership boundary
+
+This document owns semantic classification, fatal versus request-scoped
+failure, cross-process error context, compatibility policy, sanitization, and
+offline, HTTP, SSE, WebSocket, and asynchronous-job rendering rules.
+
+`engine/messages.py` remains primarily owned by the I/O contract; this page
+owns the semantics of its error fields. Route and serving files remain
+primarily owned by `entrypoints.md`; this page owns their rendering
+constraints.
+
+## Candidate invariants
+
+The following topics require owner review before receiving stable IDs:
+
+- A request-scoped failure terminates only the affected request unless the
+  underlying engine is no longer usable.
+- Every public rendering path preserves a stable classification while
+  removing sensitive internal context.
+- Cancellation remains distinguishable from internal failure across process
+  and protocol boundaries.
+
+## Invariant namespace
+
+`ERR-INV` reserves `001-099` for classification ownership, `100-199` for wire
+context and compatibility, `200-299` for fatality, termination, sanitization,
+and rendering, and `300-399` for upstream alignment and transport extension
+points. Numbers become append-only after normative promotion.
+
+## Safe-change guide
+
+Exercise exception classification, stage wire round trips, fatal and
+request-scoped propagation, cancellation, sanitization, offline exceptions,
+HTTP status/body consistency, streaming terminal events, asynchronous-job
+persistence, and metrics classification.
+
+## Promotion gate
+
+- Resolve #5570's hierarchy, wire record, sanitization, and mixed-version
+  questions.
+- Add table-driven exception/status/type tests and stage wire round trips.
+- Verify all public transports terminate once and do not leak sensitive
+  payload data.
+- Obtain approval from both technical owners and an independent validation
+  reviewer.

docs/design/module/execution_platforms.md

@@ -0,0 +1,55 @@
+---
+title: Execution Platforms
+kind: module
+status: draft
+owners:
+  - "@gcanlin"
+  - "@tjtanaa"
+  - "@xuechendi"
+primary_code_paths:
+  - vllm_omni/platforms/**
+  - vllm_omni/attention/**
+primary_code_path_owners:
+  # Additional owners scoped to attention kernels (quantized/custom attention)
+  - paths:
+      - vllm_omni/attention/**
+    owners:
+      - "@david6666666"
+      - "@lishunyang12"
+related_code_paths: []
+depends_on:
+  - ar_runtime.md
+  - diffusion/index.md
+validation_paths:
+  - tests/platforms/**
+upstream_refs:
+  - vllm.platforms
+last_reviewed: 2026-07-16
+---
+
+# Execution platforms
+
+Execution platforms isolate hardware-specific capability detection, worker
+selection, patches, kernels, and configuration adjustments.
+
+## Candidate invariants
+
+### PLATFORM-INV-001: Capabilities are explicit
+
+**Rule:** Hardware-dependent behavior MUST be guarded by platform selection or
+capability detection and MUST fail clearly when unsupported.
+
+### PLATFORM-INV-002: Portable code remains portable
+
+**Rule:** Platform-neutral modules MUST NOT import a vendor implementation
+directly when a common selection interface exists.
+
+### PLATFORM-INV-003: Overrides are minimal
+
+**Rule:** A platform implementation SHOULD override only behavior that differs
+from the common or upstream implementation.
+
+## Safe-change guide
+
+Validate common import paths without the target accelerator and run focused
+tests in a fresh `uv` environment on every affected device platform.

docs/design/module/input_output_modality_contracts.md

@@ -0,0 +1,135 @@
+---
+title: Input, Output, and Modality Contracts
+kind: module
+status: draft
+architecture_state: current
+owners:
+  - "@Sy0307"
+  - "@amy-why-3459"
+  - "@Gaohan123"
+  - "@alex-jw-brooks"
+document_stewards:
+  - "@hsliuustc0106"
+  - "@Gaohan123"
+  - "@david6666666"
+required_reviewers:
+  - "@tzhouam"
+  - "@linyueqian"
+  - "@david6666666"
+  - "@yenuo26"
+  - "@NickCao"
+primary_code_paths:
+  - vllm_omni/inputs/**
+  - vllm_omni/outputs/**
+  - vllm_omni/request.py
+  - vllm_omni/data_entry_keys.py
+  - vllm_omni/engine/messages.py
+  - vllm_omni/engine/serialization.py
+  - vllm_omni/engine/mm_outputs.py
+  - vllm_omni/engine/output_modality.py
+  - vllm_omni/engine/output_processor.py
+related_code_paths:
+  - vllm_omni/model_executor/stage_input_processors/**
+  - vllm_omni/core/sched/**
+  - vllm_omni/distributed/omni_connectors/**
+  - vllm_omni/diffusion/request.py
+  - vllm_omni/diffusion/worker/request_batch.py
+  - vllm_omni/errors.py
+depends_on:
+  - error_contracts.md
+validation_paths:
+  - tests/inputs/**
+  - tests/engine/test_data_entry_keys.py
+  - tests/engine/test_omni_request.py
+  - tests/engine/test_omni_request_output.py
+  - tests/engine/test_multimodal_accumulation.py
+  - tests/engine/test_output_modality.py
+  - tests/engine/test_output_processor.py
+  - tests/engine/test_wire_multimodal_output.py
+  - tests/utils/test_mm_outputs.py
+  - tests/utils/test_mm_outputs_partition.py
+  - tests/diffusion/test_diffusion_output_metadata.py
+upstream_refs:
+  - vllm.inputs/**
+  - vllm.outputs/**
+  - vllm.v1.request.Request
+  - vllm.v1.engine.EngineCoreRequest
+  - vllm.v1.engine.EngineCoreOutput
+  - vllm.v1.engine.output_processor.OutputProcessor
+invariant_namespace: IO-INV
+last_reviewed: 2026-08-07
+last_verified_commit: 3d7fc3b9ba3cac88d579d4dc35b78b0b641675fc
+---
+
+# Input, output, and modality contracts
+
+These contracts define the data that may cross entrypoint, orchestration,
+stage, connector, and model boundaries.
+
+## Contract status
+
+This document is a draft description of the current request, message,
+serialization, modality, accumulation, and output types. It does not assign
+semantic error ownership to the wire schema.
+
+## Ownership boundary
+
+This document owns request identity, prompt/input types, modality keys and
+metadata, queue and wire message schemas, serialization, output types,
+accumulation, completion semantics, and compatibility shims.
+
+It does not own route-specific validation or rendering, model-specific
+interpretation, connector transport mechanics, scheduling policy, or semantic
+error classification. The `ErrorMessage` schema belongs here; the meaning and
+public rendering of its error fields belong to `error_contracts.md`.
+
+## Candidate invariants
+
+These identifiers are proposals while the document is `draft`.
+
+### IO-INV-001: Boundary data has an explicit modality
+
+**Rule:** Data crossing a module or stage boundary MUST identify its modality
+and use the corresponding validated contract.
+
+### IO-INV-100: Request identity is stable
+
+**Rule:** Request identity MUST be preserved across conversions, stages,
+streaming updates, cancellation, and errors.
+
+### IO-INV-101: Completion is explicit
+
+**Rule:** Producers MUST distinguish partial updates from the terminal update
+for every output modality.
+
+### IO-INV-300: Internal objects do not leak into public protocols
+
+**Rule:** Entrypoints MUST explicitly translate internal output objects into
+public response types.
+
+## Invariant namespace
+
+`IO-INV` reserves `001-099` for schema ownership and dependency direction,
+`100-199` for identity, modality, accumulation, ordering, and completion,
+`200-299` for serialization failure and payload cleanup, and `300-399` for
+upstream extension, deprecation, and compatibility. Numbers become
+append-only after normative promotion.
+
+## Safe-change guide
+
+Test construction, validation, serialization, round trips, streaming,
+accumulation, completion, optional fields, unknown fields, and compatibility
+at every affected producer-consumer boundary.
+
+## Promotion gate
+
+- Add explicit CODEOWNERS for the primary I/O paths or confirm that fallback
+  ownership is intentional.
+- Document the compatibility window for deprecated `vllm_omni.engine`
+  I/O-related imports.
+- Verify wire round trips and rejection of unknown or incompatible schema
+  fields.
+- Define payload-versus-metadata rules and completion semantics for streaming
+  and batched outputs.
+- Obtain approval from a technical owner and independent AR, diffusion,
+  connector, entrypoint, and validation reviewers as applicable.

docs/design/module/model_integration.md

@@ -0,0 +1,59 @@
+---
+title: Model Integration
+kind: module
+status: draft
+owners:
+  - "@tzhouam"
+  - "@gcanlin"
+primary_code_paths:
+  - vllm_omni/model_executor/**
+  - vllm_omni/model_extras/**
+  - vllm_omni/plugins/**
+primary_code_path_owners:
+  # Additional owners scoped to a sub-path of model_executor/**
+  - paths:
+      - vllm_omni/model_executor/models/**
+    owners:
+      - "@Sy0307"
+      - "@amy-why-3459"
+      - "@linyueqian"
+related_code_paths:
+  - vllm_omni/transformers_utils/**
+  - vllm_omni/tokenizers/**
+depends_on:
+  - input_output_modality_contracts.md
+  - ar_runtime.md
+validation_paths:
+  - tests/model_executor/**
+  - tests/model_extras/**
+  - tests/plugin/**
+upstream_refs:
+  - vllm.model_executor
+last_reviewed: 2026-07-16
+---
+
+# Model integration
+
+Model integration adapts model-specific configuration, preprocessing, loading,
+and execution behavior to stable runtime contracts.
+
+## Candidate invariants
+
+### MODEL-INV-001: Registration is explicit
+
+**Rule:** A model integration MUST declare how its model class, loader, input
+processor, and stage configuration are selected.
+
+### MODEL-INV-002: Model code does not route stages
+
+**Rule:** Model-specific code MUST NOT select or invoke a downstream omni stage.
+
+### MODEL-INV-003: Upstream behavior is reused deliberately
+
+**Rule:** An upstream vLLM implementation SHOULD be reused when its contract is
+sufficient; an override MUST document the behavioral difference.
+
+## Safe-change guide
+
+Test registration, checkpoint loading, input conversion, and representative
+model execution. Test shared utilities against more than one integration.

docs/design/module/observability.md

@@ -0,0 +1,47 @@
+---
+title: Observability
+kind: module
+status: draft
+owners:
+  - "@lishunyang12"
+  - "@vraiti"
+primary_code_paths:
+  - vllm_omni/metrics/**
+related_code_paths:
+  - vllm_omni/engine/**
+  - vllm_omni/entrypoints/**
+depends_on:
+  - engine_orchestration.md
+validation_paths:
+  - tests/metrics/**
+upstream_refs:
+  - vllm.v1.metrics
+last_reviewed: 2026-07-16
+---
+
+# Observability
+
+Observability defines stable metrics, logs, and correlation fields for tracing a
+request across entrypoints, orchestration, stages, and workers.
+
+## Candidate invariants
+
+### OBS-INV-001: Request correlation survives stage boundaries
+
+**Rule:** Logs and metrics for the same request SHOULD carry a stable request
+identifier and stage identity.
+
+### OBS-INV-002: Metric meaning is stable
+
+**Rule:** A metric's unit, labels, aggregation, and lifecycle MUST be documented;
+changing any of them is a contract change.
+
+### OBS-INV-003: Labels are bounded
+
+**Rule:** Metrics MUST NOT use request IDs, prompts, outputs, or other unbounded
+values as labels.
+
+## Safe-change guide
+
+Test registration, label sets, units, lifecycle resets, and representative
+multi-stage emission.

docs/design/module/omni_connector.md

@@ -0,0 +1,50 @@
+---
+title: OmniConnector
+kind: module
+status: draft
+owners:
+  - "@princepride"
+  - "@yuanheng-zhao"
+  - "@xuechendi"
+  - "@natureofnature"
+  - "@fake0fan"
+primary_code_paths:
+  - vllm_omni/distributed/omni_connectors/**
+related_code_paths:
+  - vllm_omni/platforms/*/omni_connectors/**
+depends_on:
+  - input_output_modality_contracts.md
+  - vllm_omni_config.md
+validation_paths:
+  - tests/distributed/omni_connectors/**
+upstream_refs:
+  - vllm.distributed
+last_reviewed: 2026-07-16
+---
+
+# OmniConnector
+
+OmniConnector defines model-agnostic transport and synchronization contracts
+for data exchanged across stages, processes, devices, and nodes.
+
+## Candidate invariants
+
+### CONNECTOR-INV-001: Connectors transport but do not route
+
+**Rule:** A connector MUST NOT select the next stage or implement model-specific
+execution policy.
+
+### CONNECTOR-INV-002: Producer and consumer contracts agree
+
+**Rule:** Both ends MUST agree on data identity, shape, dtype, placement,
+ownership, and completion semantics.
+
+### CONNECTOR-INV-003: Resources have deterministic cleanup
+
+**Rule:** Connections, buffers, handles, and background work MUST be released on
+normal completion, cancellation, failure, and shutdown.
+
+## Safe-change guide
+
+Test setup, transfer, synchronization, timeout, cancellation, failure, and
+cleanup across every affected backend.

docs/design/module/profiling.md

@@ -0,0 +1,46 @@
+---
+title: Profiling
+kind: module
+status: draft
+owners:
+  - "@gcanlin"
+primary_code_paths:
+  - vllm_omni/profiler/**
+  - vllm_omni/diffusion/profiler/**
+related_code_paths:
+  - vllm_omni/entrypoints/**
+depends_on:
+  - observability.md
+validation_paths:
+  - tests/profile/**
+upstream_refs:
+  - vllm.profiler
+last_reviewed: 2026-07-16
+---
+
+# Profiling
+
+Profiling owns opt-in instrumentation and trace collection used to locate
+runtime bottlenecks without changing model results or execution policy.
+
+## Candidate invariants
+
+### PROFILE-INV-001: Profiling is opt-in
+
+**Rule:** Expensive trace collection MUST be disabled by default and bounded by
+an explicit start and stop lifecycle.
+
+### PROFILE-INV-002: Instrumentation preserves semantics
+
+**Rule:** Profiling MUST NOT change scheduling decisions, generated outputs, or
+resource ownership beyond documented synchronization overhead.
+
+### PROFILE-INV-003: Trace context is sufficient
+
+**Rule:** Trace events SHOULD identify stage, rank, worker, operation, and
+request where available without embedding user payloads.
+
+## Safe-change guide
+
+Test disabled overhead, repeated start and stop, cleanup, multi-rank trace
+naming, and each supported profiler backend.

docs/design/module/quantization.md

@@ -0,0 +1,50 @@
+---
+title: Quantization
+kind: module
+status: draft
+owners:
+  - "@david6666666"
+  - "@Isotr0py"
+  - "@lishunyang12"
+primary_code_paths:
+  - vllm_omni/quantization/**
+  - vllm_omni/diffusion/quantization/**
+related_code_paths:
+  - vllm_omni/platforms/*/quant/**
+depends_on:
+  - model_integration.md
+  - diffusion/diffusion_model_integration.md
+validation_paths:
+  - tests/quantization/**
+  - tests/diffusion/quantization/**
+upstream_refs:
+  - vllm.model_executor.layers.quantization
+last_reviewed: 2026-07-16
+---
+
+# Quantization
+
+Quantization owns method registration, checkpoint interpretation, layer
+replacement, and runtime constraints for reduced-precision execution.
+
+## Candidate invariants
+
+### QUANT-INV-001: Checkpoint and runtime methods agree
+
+**Rule:** The selected method MUST validate checkpoint metadata, supported
+layers, device capabilities, and required dependencies before use.
+
+### QUANT-INV-002: Unsupported combinations fail clearly
+
+**Rule:** Quantization MUST NOT silently fall back to a different precision or
+method when a requested combination is unsupported.
+
+### QUANT-INV-003: Numerical validation is required
+
+**Rule:** A new method or layer mapping MUST include correctness comparison
+against a defined reference result.
+
+## Safe-change guide
+
+Test loading, representative layers, metadata, platform guards, and numerical
+tolerances separately from performance.

docs/design/module/stage_runtime.md

@@ -0,0 +1,126 @@
+---
+title: Stage Runtime and Replica Lifecycle
+kind: module
+status: draft
+architecture_state: current-plus-in-flight
+owners:
+  - "@tzhouam"
+  - "@fake0fan"
+document_stewards:
+  - "@hsliuustc0106"
+  - "@Gaohan123"
+  - "@david6666666"
+required_reviewers:
+  - "@Sy0307"
+  - "@princepride"
+  - "@chickeyton"
+  - "@yenuo26"
+  - "@NickCao"
+primary_code_paths:
+  - vllm_omni/engine/stage_runtime.py
+  - vllm_omni/engine/stage_pool.py
+  - vllm_omni/engine/stage_client.py
+  - vllm_omni/engine/membership_controller.py
+  - vllm_omni/engine/stage_engine_startup.py
+  - vllm_omni/engine/stage_engine_core_client.py
+  - vllm_omni/engine/stage_engine_core_proc.py
+  - vllm_omni/engine/stage_engine_core_proc_manager.py
+  - vllm_omni/engine/stage_init_utils.py
+related_code_paths:
+  - vllm_omni/distributed/omni_coordinator/**
+  - vllm_omni/distributed/ray_utils/**
+  - vllm_omni/diffusion/inline_stage_diffusion_client.py
+  - vllm_omni/diffusion/stage_diffusion_client.py
+  - vllm_omni/diffusion/stage_diffusion_proc.py
+  - vllm_omni/config/**
+depends_on:
+  - input_output_modality_contracts.md
+  - error_contracts.md
+  - omni_connector.md
+validation_paths:
+  - tests/engine/test_async_omni_engine_stage_init.py
+  - tests/engine/test_membership_controller.py
+  - tests/engine/test_single_stage_mode.py
+  - tests/engine/test_stage_engine_core_client.py
+  - tests/engine/test_stage_engine_core_proc.py
+  - tests/diffusion/test_inline_stage_diffusion_client.py
+  - tests/diffusion/test_stage_diffusion_proc.py
+  - tests/distributed/omni_coordinator/**
+upstream_refs:
+  - vllm.v1.engine.core_client.AsyncMPClient
+  - vllm.v1.engine.core_client.DPLBAsyncMPClient
+  - vllm.v1.engine.core.EngineCoreProc
+  - vllm.v1.engine.utils.CoreEngineProcManager
+  - vllm.v1.engine.coordinator.DPCoordinator
+invariant_namespace: STAGE-INV
+last_reviewed: 2026-08-07
+last_verified_commit: 3d7fc3b9ba3cac88d579d4dc35b78b0b641675fc
+---
+
+# Stage runtime and replica lifecycle
+
+The stage runtime turns a logical stage definition into ready local or
+distributed replicas and provides the lifecycle boundary used by the
+orchestrator.
+
+## Contract status
+
+This document describes the current `StageRuntime`, `StagePool`, stage-client,
+and stage-process layout. The unified LLM/diffusion direction in
+[#5441](https://github.com/vllm-project/vllm-omni/pull/5441) remains in flight
+and is not presented as current behavior.
+
+## Ownership boundary
+
+This document owns local and distributed stage placement, startup and
+readiness, one pool per logical stage, replica identity and membership,
+selection and affinity, stage-client/process lifecycle, liveness, draining,
+and shutdown.
+
+It does not own cross-stage request policy, model scheduler policy, connector
+transfer semantics, configuration precedence, or public error rendering.
+
+## Candidate invariants
+
+These identifiers are proposals while the document is `draft`.
+
+### STAGE-INV-001: The runtime owns replica lifecycle
+
+**Rule:** Orchestration MUST acquire stage capacity through the stage runtime
+and MUST NOT construct or retire backend replicas directly.
+
+### STAGE-INV-100: Affinity uses stable replica identity
+
+**Rule:** Follow-up operations for a request with replica affinity MUST resolve
+the same logical replica until the request terminates or the replica is
+declared lost.
+
+### STAGE-INV-200: Shutdown is idempotent
+
+**Rule:** Repeated shutdown or cleanup signals MUST NOT leak stage clients,
+process managers, or membership registrations.
+
+## Invariant namespace
+
+`STAGE-INV` reserves `001-099` for placement and ownership, `100-199` for
+replica identity/readiness/affinity, `200-299` for liveness loss, draining and
+cleanup, and `300-399` for local/distributed and upstream compatibility.
+Numbers become append-only after normative promotion.
+
+## Safe-change guide
+
+Exercise local and distributed startup, readiness, replica selection,
+affinity, membership changes, abort routing, process failure, draining, and
+repeated shutdown. Cross-stage policy changes belong in
+`engine_orchestration.md`.
+
+## Promotion gate
+
+- Reconcile terminology and ownership after #5441 reaches a final state.
+- Add or identify a dedicated StageRuntime/StagePool lifecycle suite; current
+  evidence is distributed across the cited tests.
+- Demonstrate affinity preservation for update, interaction, and abort paths.
+- Demonstrate membership loss and repeated shutdown without leaked clients or
+  processes.
+- Obtain approval from a technical owner and an independent validation
+  reviewer.

docs/design/module/vllm_omni_config.md

@@ -0,0 +1,56 @@
+---
+title: vLLM-Omni Configuration
+kind: module
+status: draft
+architecture_state: deferred-pending-refactor
+ownership_status: provisional
+owners:
+  - "@lishunyang12"
+  - "@alex-jw-brooks"
+primary_code_paths:
+  - vllm_omni/config/**
+  - vllm_omni/deploy/**
+  - vllm_omni/model_executor/stage_configs/**
+related_code_paths:
+  - vllm_omni/platforms/*/stage_configs/**
+depends_on: []
+validation_paths:
+  - tests/config/**
+upstream_refs:
+  - vllm.config
+last_reviewed: 2026-08-07
+last_verified_commit: 3d7fc3b9ba3cac88d579d4dc35b78b0b641675fc
+---
+
+# vLLM-Omni configuration
+
+This page intentionally records discovery paths only. Substantive
+configuration ownership and contract work is deferred until the active
+configuration refactoring has settled.
+
+## Deferred contract scope
+
+The current code and tests remain authoritative for parsing, defaults,
+overrides, deployment topology, stage construction, and runtime projection.
+This draft does not define a stable precedence model, environment-variable
+capture rule, canonical configuration object, or invariant namespace.
+
+The PR review proposal to capture environment-derived values in configuration
+objects at initialization is an open design question, not a current
+invariant.
+
+## Safe-change guide while deferred
+
+Changes should trace every affected producer to its runtime consumer and test
+the structured, legacy, CLI, and deployment paths that are actually supported.
+Do not infer a stable contract from this placeholder page.
+
+## Promotion gate
+
+- Finish or stabilize the configuration refactor and identify the canonical
+  runtime configuration representation.
+- Confirm technical owners, primary path exceptions, and validation owners.
+- Document parsing and override precedence, including when environment values
+  are captured.
+- Allocate an invariant namespace only after those behaviors are enforced and
+  owner-approved.

docs/features/session_state_manager.md

@@ -20,11 +20,12 @@ extracts it into a shared, typed contract:
   (matching the bespoke caches it replaces), and reports per-device byte usage
   via `stats()` for observability.
 
-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.
+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.
 
 ## Enabling
 
@@ -158,3 +159,62 @@ 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.

docs/mkdocs/hooks/generate_argparse.py

@@ -123,6 +123,7 @@ 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,

docs/mkdocs/hooks/generate_examples.py

@@ -24,6 +24,23 @@ SERVING_MODE_TITLES = {
     "online_serving": "Online serving",
 }
 
+# Keep the Examples navigation focused on reusable modality/task entry points.
+# Model-specific scripts remain available under ``examples/`` and are surfaced
+# from these shared pages instead of getting one page per model.
+GENERAL_EXAMPLE_SLUGS = frozenset(
+    {
+        "image_to_image",
+        "image_to_video",
+        "speech_to_video",
+        "text_to_audio",
+        "text_to_image",
+        "text_to_speech",
+        "text_to_video",
+        "x_to_text",
+        "x_to_video_audio",
+    }
+)
+
 
 def load_model_display_names() -> dict[str, str]:
     try:
@@ -46,6 +63,13 @@ def load_model_display_names() -> dict[str, str]:
 MODEL_DISPLAY_NAMES = load_model_display_names()
 
 
+def is_general_example(example: "Example") -> bool:
+    """Return whether an example should get a generated serving page."""
+    if example.category not in SERVING_MODE_TITLES:
+        return True
+    return example.path.stem in GENERAL_EXAMPLE_SLUGS
+
+
 def fix_case(text: str) -> str:
     subs = {
         "api": "API",
@@ -340,22 +364,21 @@ def update_nav_file(examples: list[Example]):
             examples_by_category[category] = []
         examples_by_category[category].append(example)
 
-    # 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:
+    def category_items(category: str) -> list[dict[str, str]]:
+        items = []
+        for example in sorted(examples_by_category[category], key=lambda e: e.path.stem):
             doc_path = EXAMPLE_DOC_DIR / example.category / f"{example.path.stem}.md"
             rel_path = doc_path.relative_to(ROOT_DIR / "docs")
-            category_items.append({example.nav_title: rel_path.as_posix()})
+            items.append({example.nav_title: rel_path.as_posix()})
+        return items
 
-        if category_items:
-            # Format category name (e.g., "offline_inference" -> "Offline Inference")
+    # Build the new Examples section - start with preserved items.
+    examples_section = preserved_items.copy()
+    for category in sorted(examples_by_category.keys()):
+        items = category_items(category)
+        if items:
             category_title = fix_case(category.replace("_", " ").title())
-            examples_section.append({category_title: category_items})
+            examples_section.append({category_title: items})
 
     # Update the nav structure
     nav_list[user_guide_idx]["User Guide"][examples_idx]["Examples"] = examples_section
@@ -390,6 +413,8 @@ def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
         for path in category.glob("*/*.md"):
             examples.append(Example(path.parent, category.stem))
 
+    examples = [example for example in examples if is_general_example(example)]
+
     # Generate the example documentation
     for example in sorted(examples, key=lambda e: e.path.stem):
         example_name = f"{example.path.stem}.md"

docs/models/supported_models.md

@@ -17,83 +17,99 @@ th {
 }
 </style>
 
-| 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` | ✅︎ | ✅︎ | | |
+| 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.
 
 ✅︎ 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.

docs/user_guide/diffusion/attention_backends.md

@@ -17,7 +17,7 @@ The full set of backends and their platform defaults is in the **Backend Options
 | `TRTLLM_ATTN` | FlashInfer's trtllm-gen FMHA (TensorRT-LLM's generated kernels, vendored by FlashInfer). Dense BF16, GQA native, `head_dim=128`. Datacenter Blackwell only (sm_100 / sm_103). Packed paths can provide `cu_seqlens` directly. Supports optional **Skip-Softmax** sparse attention — see below. Requires `flashinfer`. |
 | `FLASH_ATTN` | Wraps FlashAttention 4 on Blackwell when `flash-attn-4` is installed, then falls back to FlashAttention 3/2. Default on Hopper / Ada / Ampere when a compatible FlashAttention package is installed. |
 | `CUDNN_ATTN` | Pins `sdpa_kernel([CUDNN_ATTENTION])`. Default on Blackwell (sm_10x / sm_12x) with cuDNN ≥ 9.5. Wins on mask-heavy DiTs (HunyuanVideo-1.5: 2× e2e vs SDPA). |
-| `FLASHINFER_ATTN` | Calls FlashInfer's dense `single_prefill_with_kv_cache` directly with `custom_mask` for non-causal masked attention. Used as Blackwell fallback when cuDNN is unavailable. Requires `flashinfer`. |
+| `FLASHINFER_ATTN` | Uses FlashInfer's batch-prefill wrapper and supports mixed Q/K and V input dtypes through backend-specific configuration. Used as Blackwell fallback when cuDNN is unavailable. Requires `flashinfer` >= 0.6.16rc1 for mixed-dtype configurations. |
 | `TORCH_SDPA` | PyTorch `scaled_dot_product_attention` with the default backend dispatcher. Most conservative; always available. |
 | `SAGE_ATTN` | SageAttention 2.2 — INT8-quantized attention with FP16 accumulation. Lossy but typically visually indistinguishable on diffusion outputs. Requires `sageattention`. |
 | `SAGE_ATTN_3` | Requires `sageattn3` from `SageAttention/sageattention3_blackwell`. CUDA only, intended for Blackwell GPUs, with GQA/MQA requests falling back to PyTorch SDPA. |
@@ -84,7 +84,7 @@ A backend that needs configuration exposes it as a typed field on the spec:
 When constructing `OmniDiffusionConfig` directly:
 
 ```python
-from vllm_omni.diffusion.data import AttentionConfig, AttentionSpec, OmniDiffusionConfig
+from vllm_omni.diffusion.data import AttentionConfig, AttentionSpec, AttnQuantSpec, OmniDiffusionConfig
 
 config = OmniDiffusionConfig(
     diffusion_attention_config=AttentionConfig(
@@ -99,6 +99,27 @@ config = OmniDiffusionConfig(
 
 A plain dict is also accepted and normalized to `AttentionConfig`.
 
+#### FlashInfer QK16/V8 quantized attention
+
+`FLASHINFER_ATTN` accepts quantization options through `AttentionSpec.quant`. For QK16/V8:
+
+```python
+config = OmniDiffusionConfig(
+    diffusion_attention_config=AttentionConfig(
+        default=AttentionSpec(
+            backend="FLASHINFER_ATTN",
+            quant=AttnQuantSpec(
+                dtype_qk="bfloat16",
+                dtype_vo="fp8_e4m3",
+            ),
+        ),
+    ),
+    ...,
+)
+```
+
+`dtype_qk` configures the Q and K input dtypes. `dtype_vo` configures the V input dtype.
+
 ## Platform Defaults
 
 ### Blackwell (sm_100 / sm_103 / sm_120 / sm_121)
@@ -262,23 +283,20 @@ blocks — use Ulysses SP (`ring_degree=1`).
 
 ### Which geometries run sparse
 
-Sparsity is only applied when the video segment is a **multiple of 128 rows**, where the row count
-is `latent_t × (height / 32) × (width / 32)`. Otherwise `rf_v2`'s block mask and the kernel's own
-tiling disagree on the block count, and the block straddling the seam mixes video and prefix rows
-that selection may then drop. Any resolution still runs — an unaligned geometry falls back to dense
-attention and logs `RAINFUSION_ATTN staying dense` with the row count it computed — but it gets no
-speedup, so pick an aligned geometry when you want one.
+MindIE-SD rf_v2 handles arbitrary video grids by spatially rearranging video first and, when
+necessary, promoting a real-video suffix to its always-kept prefix segment. It never pads: rf_v2
+does not consume an attention mask for padded keys. The remaining video rows stay sparse, while the
+promoted rows remain visible to every query and key.
 
-Alignment is necessary, not sufficient, for good quality. `rf_v2` groups video positions into 8x8
-spatial tiles (two tiles fill one 128-row block), which is what makes a selected block a compact
-patch of the frame. When the latent `h` or `w` is not a multiple of 8, the leftover rows or columns
-are peeled off and appended as a flat run instead of being tiled, so they get pooled with spatially
-distant positions and selection can no longer rank them meaningfully. This is silent, and invisible
-to a `sparsity=0` check, because a fully populated mask does not care how blocks are grouped.
+For example, MiniMax-H3 at 1344x768 has grid `(62, 24, 42)`: its 62496 video rows leave a 32-row
+128-block residue, and its two non-8-wide latent columns form a 2928-row rearranged suffix.
+MindIE-SD promotes 2976 rows, leaving 59520 sparse rows (`465 × 128`). This keeps the block mask
+and kernel tiling aligned, at the cost of retaining more blocks.
 
-"Multiple of 8" on the latent grid means **width and height that are multiples of 256**. Aligned
-resolutions off that grid still run sparse; they just lose more fidelity at the same `sparsity`,
-which you can buy back with `start_step`.
+8x8-aligned spatial grids remain preferable for performance. A latent `h` or `w` not divisible by 8
+creates an always-kept residual suffix and lowers realized sparsity. "Multiple of 8" on the latent
+grid means **width and height that are multiples of 256**. This path requires a MindIE-SD release
+that implements protected video tails for rf_v2.
 
 ## End-to-End Benchmark (BF16, sm_120 RTX Pro 6000 Blackwell)
 

docs/user_guide/diffusion/cache_acceleration/cache_dit.md

@@ -6,6 +6,7 @@
 - [Overview](#overview)
 - [Quick Start](#quick-start)
 - [Example Script](#example-script)
+- [Request-Scoped Quality](#request-scoped-quality-minimax-h3)
 - [Acceleration Methods](#acceleration-methods)
 - [Configuration Parameters](#configuration-parameters)
 - [Best Practices](#best-practices)
@@ -140,6 +141,43 @@ vllm serve Qwen/Qwen-Image --omni --port 8091 \
   --cache-config '{"Fn_compute_blocks": 1, "residual_diff_threshold": 0.12}'
 ```
 
+## Request-Scoped Quality (MiniMax H3)
+
+MiniMax H3 can switch Cache-DiT at the request boundary without enabling a
+cache backend at server startup. Add a quality field to an online request:
+
+```bash
+# Native reference path for this request.
+-F 'quality=lossless'
+
+# H3's conservative Cache-DiT profile for this request.
+-F 'quality=high'
+```
+
+For offline inference, set the same field on the sampling parameters:
+
+```python
+OmniDiffusionSamplingParams(
+    quality="high",
+    num_inference_steps=50,
+    extra_args={"task": "t2va", "duration": 5.0, "audio_flow_shift": 3.0},
+)
+```
+
+| Server startup | Request quality | Behavior |
+|---|---|---|
+| `--cache-backend cache_dit` | omitted | Use or restore the startup Cache-DiT profile |
+| `--cache-backend cache_dit` | `lossless` | Remove Cache-DiT hooks and run the reference path |
+| `--cache-backend cache_dit` | `high` | Use or install H3's conservative Cache-DiT profile |
+| no Cache-DiT | omitted or `lossless` | Run the reference path |
+| no Cache-DiT | `high` | Install H3's conservative Cache-DiT profile |
+
+The startup option is only needed when omitted-quality requests should use the
+server-configured Cache-DiT profile by default.
+
+See the [MiniMax H3 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3.md#request-scoped-quality)
+for a complete request and measured trade-off.
+
 ---
 
 ## Acceleration Methods

docs/user_guide/diffusion_features.md

@@ -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**               |     ❌     |     ✅      |           ✅           |       ❌        |       ✅ (DiT/TE)  |         ❌         |   ✅    |             ✅             |       ✅ (tile)       |      ✅ (DiT)      |        ❌         |
+| **MiniMax-H3**               | ✅ (FL2VA) |     ✅      |           ✅           |       ❌        |       ✅ (DiT/TE)  |         ❌         |   ✅    |             ✅             |       ✅ (tile)       |      ✅ (DiT)      |        ❌         |
 
 **Frame Interpolation Support**
 

docs/user_guide/examples/online_serving/diffusers_pipeline_adapter.md

@@ -99,7 +99,7 @@ a native vLLM-Omni pipeline for those cases.
 ### Attention Backends
 
 The diffusers backend converts
-[vLLM-Omni standard of attention backend setting](../../../docs/user_guide/diffusion/attention_backends.md)
+[vLLM-Omni standard of attention backend setting](../../diffusion/attention_backends.md)
 to [diffusers standard](https://huggingface.co/docs/diffusers/optimization/attention_backends#available-backends).
 
 Specifically for `FLASH_ATTN`, it will first attempt to use FlashAttention-3 and then FlashAttention-2.

examples/offline_inference/image_to_video/README.md

@@ -33,6 +33,25 @@ 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:

examples/offline_inference/minimax_h3/dlo_dp2_lifecycle.py

@@ -0,0 +1,240 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Reproduce MiniMax-H3 request-mode and DLO/DP2 lifecycle behavior.
+
+Examples:
+
+    VLLM_WORKER_MULTIPROC_METHOD=spawn \
+    VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400 \
+    VLLM_OMNI_DLO_DP_WAVE_TIMEOUT=600 \
+    CUDA_VISIBLE_DEVICES=0,1 \
+    python examples/offline_inference/minimax_h3/dlo_dp2_lifecycle.py \
+        --model /path/to/MiniMax-H3/FL2VA --mode dlo-dp2
+
+    VLLM_WORKER_MULTIPROC_METHOD=spawn \
+    VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400 \
+    CUDA_VISIBLE_DEVICES=0,1 \
+    python examples/offline_inference/minimax_h3/dlo_dp2_lifecycle.py \
+        --model /path/to/MiniMax-H3/FL2VA --mode request
+"""
+
+from __future__ import annotations
+
+import argparse
+import asyncio
+import copy
+import json
+import multiprocessing
+import time
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+
+from vllm_omni.entrypoints.async_omni import AsyncOmni
+
+DEFAULT_PROMPTS = (
+    "At night, three cats march into a bedroom playing tiny brass instruments, "
+    "then abruptly file out, with synchronized room ambience.",
+    "A paper boat crosses a rain-filled street while distant traffic and water sounds remain synchronized.",
+)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--model", required=True, help="Path to MiniMax-H3/FL2VA")
+    parser.add_argument(
+        "--mode",
+        choices=("dlo-dp2", "request"),
+        required=True,
+        help="DLO AllGather DP2 or ordinary non-DLO TP2 request mode",
+    )
+    parser.add_argument("--steps", type=int, default=2)
+    parser.add_argument("--duration", type=float, default=5.0)
+    parser.add_argument("--width", type=int, default=1344)
+    parser.add_argument("--height", type=int, default=768)
+    parser.add_argument("--batch-wait-ms", type=float, default=500.0)
+    parser.add_argument("--init-timeout", type=float, default=1800.0)
+    parser.add_argument("--output", type=Path)
+    return parser.parse_args()
+
+
+def engine_kwargs(args: argparse.Namespace) -> dict[str, Any]:
+    common: dict[str, Any] = {
+        "model": args.model,
+        "trust_remote_code": True,
+        "num_gpus": 2,
+        "usp": 1,
+        "ring": 1,
+        "vae_parallel_mode": "tile",
+        "vae_use_tiling": True,
+        "diffusion_attention_backend": "CUDNN_ATTN",
+        "request_batch_max_wait_ms": args.batch_wait_ms,
+        "enforce_eager": True,
+        "stage_init_timeout": args.init_timeout,
+        "init_timeout": args.init_timeout,
+    }
+    if args.mode == "dlo-dp2":
+        common.update(
+            tensor_parallel_size=1,
+            data_parallel_size=2,
+            text_encoder_tp_size=1,
+            vae_patch_parallel_size=1,
+            enable_distributed_layerwise_offload=True,
+            dlo_use_allgather=True,
+            dlo_resident_layers=0,
+        )
+    else:
+        common.update(
+            tensor_parallel_size=2,
+            data_parallel_size=1,
+            text_encoder_tp_size=2,
+            vae_patch_parallel_size=2,
+            enable_distributed_layerwise_offload=False,
+        )
+    return common
+
+
+def sampling_params(
+    engine: AsyncOmni,
+    args: argparse.Namespace,
+    seed: int,
+) -> list[Any]:
+    params = copy.deepcopy(engine.default_sampling_params_list)
+    diffusion = params[0]
+    diffusion.width = args.width
+    diffusion.height = args.height
+    diffusion.fps = 24
+    diffusion.num_inference_steps = args.steps
+    diffusion.seed = seed
+    diffusion.extra_args = {
+        "task": "t2va",
+        "duration": args.duration,
+        "aspect_ratio": "16:9",
+        "flow_shift": 12.0,
+        "audio_flow_shift": 3.0,
+    }
+    return params
+
+
+async def generate_one(
+    engine: AsyncOmni,
+    args: argparse.Namespace,
+    *,
+    request_id: str,
+    prompt: str,
+    seed: int,
+) -> Any:
+    final_output = None
+    async for output in engine.generate(
+        prompt=prompt,
+        request_id=request_id,
+        sampling_params_list=sampling_params(engine, args, seed),
+    ):
+        if output.finished:
+            final_output = output
+    if final_output is None:
+        raise RuntimeError(f"{request_id} finished without an output")
+    return final_output
+
+
+def output_summary(output: Any, args: argparse.Namespace) -> dict[str, Any]:
+    if not output.images:
+        raise RuntimeError(f"{output.request_id} returned no video")
+    frames = np.asarray(output.images[0])
+    audio = np.asarray(output.multimodal_output.get("audio"))
+    if frames.ndim != 4 or tuple(frames.shape[1:]) != (
+        args.height,
+        args.width,
+        3,
+    ):
+        raise RuntimeError(f"{output.request_id} returned invalid video shape {tuple(frames.shape)}")
+    if audio.ndim != 3 or tuple(audio.shape[:2]) != (1, 2):
+        raise RuntimeError(f"{output.request_id} returned invalid audio shape {tuple(audio.shape)}")
+    if args.duration == 5.0 and args.height == 768 and args.width == 1344:
+        if tuple(frames.shape) != (124, 768, 1344, 3) or tuple(audio.shape) != (1, 2, 165600):
+            raise RuntimeError(
+                f"{output.request_id} default shape mismatch: video={tuple(frames.shape)}, audio={tuple(audio.shape)}"
+            )
+    return {
+        "request_id": output.request_id,
+        "frames_shape": list(frames.shape),
+        "audio_shape": list(audio.shape),
+        "peak_memory_mb": output.peak_memory_mb,
+        "stage_durations": output.stage_durations,
+    }
+
+
+async def run(args: argparse.Namespace) -> dict[str, Any]:
+    engine = AsyncOmni(**engine_kwargs(args))
+    summary: dict[str, Any] = {
+        "mode": args.mode,
+        "engine_kwargs": engine_kwargs(args),
+    }
+    try:
+        if args.mode == "dlo-dp2":
+            started = time.perf_counter()
+            asymmetric = await asyncio.gather(
+                generate_one(
+                    engine,
+                    args,
+                    request_id="invalid-empty",
+                    prompt="",
+                    seed=1001,
+                ),
+                generate_one(
+                    engine,
+                    args,
+                    request_id="invalid-peer",
+                    prompt=DEFAULT_PROMPTS[0],
+                    seed=1002,
+                ),
+                return_exceptions=True,
+            )
+            summary["asymmetric_wave_s"] = time.perf_counter() - started
+            summary["asymmetric_errors"] = [
+                f"{type(result).__name__}: {result}" for result in asymmetric if isinstance(result, BaseException)
+            ]
+            if len(summary["asymmetric_errors"]) != 2:
+                raise RuntimeError("Both requests in the asymmetric DP wave must fail before dispatch")
+
+        started = time.perf_counter()
+        request_count = 2 if args.mode == "dlo-dp2" else 1
+        outputs = await asyncio.gather(
+            *(
+                generate_one(
+                    engine,
+                    args,
+                    request_id=f"recovery-{index}",
+                    prompt=DEFAULT_PROMPTS[index],
+                    seed=2000 + index,
+                )
+                for index in range(request_count)
+            )
+        )
+        summary["valid_wave_s"] = time.perf_counter() - started
+        summary["outputs"] = [output_summary(output, args) for output in outputs]
+    finally:
+        started = time.perf_counter()
+        engine.close()
+        summary["shutdown_s"] = time.perf_counter() - started
+
+    children = multiprocessing.active_children()
+    summary["active_children"] = [{"name": child.name, "pid": child.pid} for child in children]
+    if children:
+        raise RuntimeError(f"Worker processes remain after shutdown: {children}")
+    return summary
+
+
+def main() -> None:
+    args = parse_args()
+    summary = asyncio.run(run(args))
+    rendered = json.dumps(summary, indent=2, sort_keys=True)
+    print(f"E2E_RESULT {rendered}", flush=True)
+    if args.output is not None:
+        args.output.parent.mkdir(parents=True, exist_ok=True)
+        args.output.write_text(rendered + "\n", encoding="utf-8")
+
+
+if __name__ == "__main__":
+    main()

examples/offline_inference/text_to_image/README.md

@@ -43,6 +43,23 @@ 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

examples/offline_inference/text_to_video/text_to_video.md

@@ -55,6 +55,21 @@ 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

examples/offline_inference/text_to_video/text_to_video_lingbot.py

@@ -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="/home/models/lingbot-video-dense-1.3b")
+    parser.add_argument("--model", default="robbyant/lingbot-video-dense-1.3b")
     parser.add_argument("--prompt", default="a robotic arm picks up a red block")
-    parser.add_argument("--negative-prompt", default="")
+    parser.add_argument("--negative-prompt", default=None)
     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)
@@ -58,9 +58,12 @@ 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.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)
+            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)
         if tensor.is_floating_point():
             if float(tensor.min()) < 0.0:
                 tensor = tensor.clamp(-1, 1) * 0.5 + 0.5
@@ -87,8 +90,12 @@ def main() -> None:
         parallel_config=DiffusionParallelConfig(),
     )
 
-    prompt: dict[str, str] = {"prompt": args.prompt}
-    if args.negative_prompt:
+    prompt: dict[str, Any] = {
+        "prompt": args.prompt,
+        "modalities": ["video"],
+        "num_frames": args.num_frames,
+    }
+    if args.negative_prompt is not None:
         prompt["negative_prompt"] = args.negative_prompt
 
     sampling_params = OmniDiffusionSamplingParams(

examples/online_serving/lingbot_video/README.md

@@ -0,0 +1,74 @@
+# 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.

examples/online_serving/lingbot_video/run_curl_text_image_to_video.sh

@@ -0,0 +1,67 @@
+#!/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}"

examples/online_serving/lingbot_video/run_curl_text_to_image.sh

@@ -0,0 +1,20 @@
+#!/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}"

examples/online_serving/lingbot_video/run_server.sh

@@ -0,0 +1,10 @@
+#!/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}"

examples/quantization/check_modelopt_fp8_export.py

@@ -1,247 +0,0 @@
-#!/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()

examples/quantization/quantize_hunyuanvideo_15_modelopt_fp8.py

@@ -1,448 +0,0 @@
-#!/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()

examples/quantization/quantize_wan2_2_modelopt_fp8.py

@@ -1,471 +0,0 @@
-#!/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()

recipes/MiniMaxAI/MiniMax-H3-NPU.md

@@ -79,7 +79,8 @@ sharing the tokenizer, processor, text encoder, and VAEs from `FL2VA`.
 ### Multi-NPU: 768P combined-service configuration
 
 Use Ulysses sequence parallelism degree 8, text-encoder tensor parallelism
-degree 8, native tiled VAE patch parallelism degree 8, and layerwise offload:
+degree 8, native tiled VAE patch parallelism degree 8, and distributed
+layerwise offload:
 
 ```bash
 export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
@@ -98,7 +99,7 @@ vllm serve "${MODEL}" \
   --usp 8 \
   --ring 1 \
   --text-encoder-tp-size 8 \
-  --enable-layerwise-offload \
+  --enable-distributed-layerwise-offload \
   --vae-parallel-mode tile \
   --vae-use-tiling \
   --vae-patch-parallel-size 8 \
@@ -112,6 +113,11 @@ H3 is CFG-distilled, so `--cfg-parallel-size` must remain 1.
 The same endpoint accepts `task=t2va`, `task=fl2va`, and `task=ref2va`; no
 partition restart is required. Layerwise offload applies to both DiTs.
 
+On Atlas 800I A3 (64 GB HBM per device) the combined service does not fit at
+768P without offloading or sharding: use distributed layerwise offload (as
+above) or HSDP — see
+[§ Memory and attention optimizations](#memory-and-attention-optimizations-a3).
+
 ### Optional optimizations
 
 Two independent optimizations may be enabled on top of the configuration
@@ -134,6 +140,63 @@ Keep `--ring 1` when using RainFusion: the `rf_v2` kernel ranks key blocks
 over the whole sequence, so ring parallelism would split away the keys it
 needs. Scale with `--usp` instead.
 
+## Memory and attention optimizations (A3)
+
+### Fitting 768P into 64 GB HBM: distributed layerwise offload or HSDP
+
+Each Atlas 800I A3 NPU has 64 GB of HBM, which is not enough for the
+combined MiniMax-H3 service at 768P. Enable **one** of the following at
+server startup:
+
+**Distributed layerwise offload** — DiT layers are offloaded with parameters
+gathered across the parallel group instead of replicated per rank:
+
+```bash
+  --enable-distributed-layerwise-offload
+```
+
+Measured peak NPU memory is about 45 GB per device for Ref2VA with a 13.88 s
+input video generating a 15 s 768P (1344x768) output video. Host (CPU) memory
+usage is high with this option.
+
+**HSDP** — hybrid sharded data parallelism for the DiT parameters. The
+multi-stream memory-reuse knob is mandatory with this flag:
+
+```bash
+export MULTI_STREAM_MEMORY_REUSE=2
+```
+
+```bash
+  --use-hsdp
+```
+
+Host memory usage is small, but large shapes may still OOM; HBM usage
+optimizations for this path are ongoing.
+
+### FLASH_ATTN backend with MindIE-SD
+
+Keep `--diffusion-attention-backend FLASH_ATTN` and install MindIE-SD (see
+[§ Environment](#environment)). On NPU this backend carries most of the
+memory-reduction and performance work: a mask-free packed varlen path that
+never materializes the quadratic `full_qk` padding mask, and K/V prefix
+slicing, both driven by the packed `cu_seqlens` metadata emitted by the H3
+transformer.
+
+### Optional: LaserAttention fused kernel
+
+For an additional attention speedup, select the Ascend LaserAttention fused
+kernel before starting the server:
+
+```bash
+export MINDIE_SD_FA_TYPE="ascend_laser_attention"
+```
+
+This requires the FLASH_ATTN backend and MindIE-SD. H3 automatically applies
+exact power-of-two input pre-scaling (`laser_input_scale=256`) so the
+kernel's fp16 workspace cannot overflow on outlier activations. Measured
+speedup numbers will be added here.
+
+
 ## HTTP API examples
 
 The request format is identical to the GPU recipe; see
@@ -154,8 +217,8 @@ configuration above:
 
 | Workload | Configuration |
 |----------|---------------|
-| T2VA, 209 frames, 1344x768 | TE TP8, layerwise offload, Ulysses 8, VPP8 tile, regional compile |
-| Ref2VA (prompt + video), 124 frames, 1344x768 | TE TP8, layerwise offload, Ulysses 8, VPP8 tile, regional compile |
+| T2VA, 209 frames, 1344x768 | TE TP8, distributed layerwise offload, Ulysses 8, VPP8 tile, regional compile |
+| Ref2VA (prompt + video), 124 frames, 1344x768 | TE TP8, distributed layerwise offload, Ulysses 8, VPP8 tile, regional compile |
 
 These measurements describe the validated shapes rather than a general
 throughput guarantee.

recipes/MiniMaxAI/MiniMax-H3-RTX-PRO-6000.md

@@ -0,0 +1,346 @@
+# 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
+```

recipes/MiniMaxAI/MiniMax-H3-Spark-GB10.md

@@ -0,0 +1,262 @@
+# 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.
+```

recipes/MiniMaxAI/MiniMax-H3.md

@@ -58,6 +58,10 @@ 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.
 
@@ -387,6 +391,101 @@ 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
@@ -574,10 +673,43 @@ default. `short_edge` controls the 768-pixel canvas and must be `768`.
 outputs; the synchronous raw-MP4 endpoint returns the first output when more
 than one is requested.
 
+## Request-scoped quality
+
+Add one of these fields to any HTTP request above. No Cache-DiT startup option
+is required; H3 installs its conservative profile when a `high` request
+arrives and removes it for a `lossless` request.
+
+```bash
+-F 'quality=lossless'  # Native reference path for this request.
+-F 'quality=high'      # H3's conservative Cache-DiT profile.
+```
+
+Omitting `quality` preserves the startup default: it uses the reference path
+normally, or the server-configured profile when the server was started with
+`--cache-backend cache_dit`.
+
+The following result was measured on 4× NVIDIA H200 with SP4, text-encoder
+TP4, 1344×768, 124 frames, 24 FPS, and 50 inference steps. One full
+`lossless` warmup was excluded, followed by three fixed prompt/seed pairs in
+balanced switch order.
+
+| `quality` | Median inference latency | Speedup | SSIM vs `lossless` | PSNR vs `lossless` | Expected trade-off |
+|---|---:|---:|---:|---:|---|
+| `lossless` | 85.49 s | 1.00× | 1.0000 | exact | Native reference path |
+| `high` | 63.36 s | 1.35× | 0.9709 | 34.98 dB | Faster with measured same-seed deviation |
+
+> [!NOTE]
+> `high` selects a fixed Cache-DiT profile, but its cache hit rate and
+> resulting latency/quality trade-off may vary by hardware, topology, and
+> workload. The values above apply to this deployment and are not universal
+> guarantees. `lossless` remains the exact reference path.
+
 ## Key parameters
 
 | Parameter | Recommended value | Notes |
 |-----------|-------------------|-------|
+| `quality` | omitted or `lossless` | Request-level quality intent; `high` dynamically installs H3's conservative Cache-DiT profile |
+| `extra_params.force_refresh_step_hint` | omitted | Optional positive 1-based denoising-step hint for an active Cache-DiT request; pair with `extra_params.force_refresh_step_policy`=`once` or `repeat` |
 | `task` | `t2va`, `fl2va`, or `ref2va` | Passed in `extra_params`; selects the task-specific DiT |
 | `duration` | Workload-specific | Decimal seconds in `extra_params`; converted to H3-compatible frame count |
 | `fps` | `24` | H3 output FPS is fixed |
@@ -618,19 +750,98 @@ 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.
-- VAE patch parallelism requires size 1 or the full DiT group size and supports
-  the H3 native `tile` mode only.
+- 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.
 
 ## Additional resources
 

recipes/README.md

@@ -19,6 +19,11 @@ 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

tests/config/test_config_factory.py

@@ -1805,6 +1805,7 @@ 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")
@@ -1813,6 +1814,7 @@ 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
@@ -1829,6 +1831,7 @@ 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:

tests/config/test_omni_config.py

@@ -39,6 +39,7 @@ 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]
@@ -966,20 +967,24 @@ 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 == {}
 
@@ -994,6 +999,8 @@ 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",
             ]
         )
     )
@@ -1005,6 +1012,29 @@ 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():
@@ -1025,6 +1055,7 @@ 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",

tests/cosmos3/test_session_memory_equivalence.py

@@ -0,0 +1,192 @@
+# 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)

tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json

@@ -43,9 +43,9 @@
         ],
         "baseline": {
           "H100": {
-            "throughput_qps": 0.0434,
-            "latency_mean": 23.0654,
-            "peak_memory_mb_mean": 76360.0
+            "throughput_qps": 0.0361,
+            "latency_mean": 27.6206,
+            "peak_memory_mb_mean": 80548.0
           }
         }
       }
@@ -100,9 +100,9 @@
         ],
         "baseline": {
           "H100": {
-            "throughput_qps": 0.0606,
-            "latency_mean": 16.4928,
-            "peak_memory_mb_mean": 47164.8
+            "throughput_qps": 0.05263,
+            "latency_mean": 18.9415,
+            "peak_memory_mb_mean": 50053.7
           }
         }
       },
@@ -127,9 +127,9 @@
         ],
         "baseline": {
           "H100": {
-            "throughput_qps": 0.0124,
-            "latency_mean": 80.7784,
-            "peak_memory_mb_mean": 55374.3429
+            "throughput_qps": 0.009595,
+            "latency_mean": 104.1058,
+            "peak_memory_mb_mean": 59718.0
           }
         }
       }