docs(review): enforce configuration provenance

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

.buildkite/common/ci_mirror_hardwares.yml

@@ -8,7 +8,7 @@
 # NPU naming: {queue}_{resource_class}
 #   a2b3_npu_1  — ascend-a2b3, resource_class npu-1 (A2/B3 CI image)
 #   a2b3_npu_4  — ascend-a2b3, resource_class npu-4
-#   a3_npu_2    — ascend-a3, resource_class npu-2
+#   a3_npu_2    — ascend-a3, resource_class npu-2 (A3 CI image tag …:$BUILDKITE_COMMIT-a3)
 
 x-npu-k8s-plugins: &npu_k8s_plugins
   - kubernetes:

.buildkite/cuda/test-merge.yml

@@ -139,11 +139,6 @@ steps:
         timeout_in_minutes: 50
         commands:
           - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        # h100_2, not h100_1: advanced_model asserts transcribe every audio
-        # response with Whisper, and tests/helpers/media.py only uses an
-        # accelerator for Whisper when a spare GPU exists. On a single card it
-        # grades on CPU: ~8-10 min per clip vs ~30 s, which alone overruns the
-        # 50-minute job timeout (build 2956).
         mirror_hardwares: h100_2
 
       - label: "Omni · MiniCPM-o 4.5 Duplex Test"
@@ -153,10 +148,10 @@ steps:
           - tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
           - tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
           - tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py
-          - tests/e2e/online_serving/helpers/minicpmo_realtime_duplex_scenarios.py
+          - tests/e2e/online_serving/minicpmo_realtime_duplex_scenarios.py
           - tests/e2e/online_serving/run_minicpmo_realtime_duplex_multi_session.py
           - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
-          - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
+          - tests/helpers/minicpmo_4_5_duplex.py
           - vllm_omni/deploy/minicpmo_4_5_duplex.yaml
           - vllm_omni/experimental/fullduplex/
           - vllm_omni/model_executor/models/minicpmo_4_5/
@@ -169,7 +164,7 @@ steps:
         timeout_in_minutes: 50
         commands:
           - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        mirror_hardwares: h100_1
+        mirror_hardwares: h100_2
 
       - label: "TTS · VoxCPM2 Test"
         source_file_dependencies:

.buildkite/cuda/test-nightly.yml

@@ -22,7 +22,7 @@ steps:
         timeout_in_minutes: 50
         commands:
           - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py -m "full_model and cuda and H100 and omni" --run-level "full_model"
-        mirror_hardwares: h100_1
+        mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · Doc Test with L4"
         timeout_in_minutes: 90
@@ -50,19 +50,6 @@ steps:
             exit $$EXIT
         mirror_hardwares: h100_2
 
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - export SEED_TTS_WER_EVAL=1
-          - export SEED_TTS_EVAL_DEVICE=cuda:1
-          - |
-            set +e
-            pytest -s -v tests/e2e/accuracy/minicpmo_4_5/test_minicpmo_4_5.py -m "full_model and cuda" --run-level full_model
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/e2e/accuracy/minicpmo_4_5/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
       - label: ":full_moon: Omni · Perf Test · No Async Chunk"
         key: nightly-omni-performance-no-async-chunk
         timeout_in_minutes: 300
@@ -115,32 +102,6 @@ steps:
             exit $$EXIT
         mirror_hardwares: h100_3
 
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Perf Test"
-        key: nightly-omni-performance-minicpmo-4-5
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Duplex Seed-TTS Perf Test"
-        key: nightly-omni-performance-minicpmo-4-5-duplex-seed-tts
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5_duplex_seed_tts.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
       - label: ":full_moon: Omni · Multi-Replica Startup Test with 4x H100"
         timeout_in_minutes: 45
         commands:
@@ -443,7 +404,7 @@ steps:
       - label: ":full_moon: Diffusion X2V · LingBot Video MoE Function Test"
         timeout_in_minutes: 90
         commands:
-          - pytest -s -v tests/e2e/online_serving/test_lingbot_video_moe.py -k "video_generation" -m "full_model and cuda" --run-level "full_model"
+          - pytest -s -v tests/e2e/online_serving/test_lingbot_video_moe.py -m "full_model and cuda" --run-level "full_model"
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2V · Doc Test"
@@ -466,10 +427,10 @@ steps:
           - pytest -s -v tests/e2e/accuracy/test_diffusers_backend_similarity.py -k '2v_matches_diffusers' -m full_model --run-level full_model
         mirror_hardwares: h100_2
 
-      - label: ":full_moon: Diffusion X2V · MiniMax H3 I2VA/Ref2VA Accuracy Test"
+      - label: ":full_moon: Diffusion X2V · MiniMax H3 T2VA Accuracy Test"
         timeout_in_minutes: 180
         commands:
-          - pytest -s -v tests/e2e/accuracy/minimax_h3/test_minimax_h3_i2va_ref2va_similarity.py -m full_model --run-level full_model
+          - pytest -s -v tests/e2e/accuracy/minimax_h3/test_minimax_h3_t2va_similarity.py -m full_model --run-level full_model
         mirror_hardwares: h100_4
 
       - label: ":full_moon: Diffusion X2V · Other Accuracy Test"

.buildkite/cuda/test-ready.yml

@@ -128,21 +128,6 @@ steps:
               image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
               always-pull: true
               propagate-environment: true
-              # vLLM 0.27 added a pre-flight capacity check in
-              # distributed/device_communicators/shm_broadcast.py. Without this
-              # the container gets Docker's 64 MiB default and every test in
-              # this step dies at engine start with
-              #   RuntimeError: Insufficient space in /dev/shm:
-              #                 240 MiB required, 64 MiB available
-              # (9 failed in 8.7s on build #2949). vLLM 0.26 had no such check
-              # and allocated regardless, so this step passed on main while
-              # being under-provisioned the whole time — 0.27 turned a silent
-              # risk into an explicit error.
-              #
-              # This is the only inline docker plugin block in .buildkite/cuda/;
-              # every other step inherits common/ci_mirror_hardwares.yml, which
-              # already sets 8gb. Matching that rather than inventing a value.
-              shm-size: "8gb"
               environment:
                 - "HF_HOME=/fsx/hf_cache"
               volumes:
@@ -187,7 +172,7 @@ steps:
             timeout 20m bash -c "
               pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py -m 'core_model' --run-level 'core_model'
             "
-        mirror_hardwares: h100_1
+        mirror_hardwares: h100_2
 
       - label: "Omni · MiniCPM-o 4.5 Online Test"
         source_file_dependencies:
@@ -198,7 +183,7 @@ steps:
             timeout 20m bash -c "
               pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model' --run-level 'core_model'
             "
-        mirror_hardwares: h100_1
+        mirror_hardwares: h100_2
 
       - label: "Omni · MiniCPM-o 4.5 Duplex Test"
         source_file_dependencies:
@@ -207,10 +192,10 @@ steps:
           - tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
           - tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
           - tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py
-          - tests/e2e/online_serving/helpers/minicpmo_realtime_duplex_scenarios.py
+          - tests/e2e/online_serving/minicpmo_realtime_duplex_scenarios.py
           - tests/e2e/online_serving/run_minicpmo_realtime_duplex_multi_session.py
           - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
-          - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
+          - tests/helpers/minicpmo_4_5_duplex.py
           - vllm_omni/deploy/minicpmo_4_5_duplex.yaml
           - vllm_omni/experimental/fullduplex/
           - vllm_omni/model_executor/models/minicpmo_4_5/
@@ -225,7 +210,7 @@ steps:
             timeout 20m bash -c "
               pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'core_model and cuda' --run-level 'core_model'
             "
-        mirror_hardwares: h100_1
+        mirror_hardwares: h100_2
 
       - label: "TTS · VoxCPM2 Test"
         source_file_dependencies:

.buildkite/intel/pipeline-intel.yml

@@ -10,7 +10,7 @@ steps:
           DOCKER_BUILDKIT: "1"
           # Buildkite will automatically replace this with the actual commit hash
           VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
-          VLLM_VERSION: "v0.27.0"
+          VLLM_VERSION: "v0.26.0"
         priority: 100
         timeout_in_minutes: 60
         soft_fail: false

.buildkite/intel/scripts/run-xpu-test.sh

@@ -34,23 +34,8 @@ docker_build() {
     docker build "${out[@]}" "$@" -f docker/Dockerfile.xpu .
 }
 
-build_vllm_base() (
-    local vllm_source_dir
-    vllm_source_dir=$(mktemp -d)
-    trap 'rm -rf "${vllm_source_dir}"' EXIT
-
-    git clone --depth 1 --branch "${VLLM_VERSION}" \
-        https://github.com/vllm-project/vllm "${vllm_source_dir}"
-
-    local out=("${export_args[@]/'{{IMAGE}}'/${base_image_name}}")
-    docker build "${out[@]}" \
-        --target vllm-openai \
-        -f "${vllm_source_dir}/docker/Dockerfile.xpu" \
-        "${vllm_source_dir}"
-)
-
 if [ -z "$(docker images -q "${base_image_name}")" ]; then
-    build_vllm_base
+    docker_build "${base_image_name}" --target vllm-base --build-arg "VLLM_VERSION=${VLLM_VERSION}"
 fi
 
 # Try building the docker image

.buildkite/npu/test-npu-nightly.yml

@@ -39,7 +39,7 @@ steps:
             EXIT=$$?
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 Test"
+      - label: ":robot: Omni · MiniCPM-o 4.5 Test"
         mirror_hardwares: a3_npu_2
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
@@ -47,34 +47,6 @@ steps:
           HF_TOKEN: "${HF_TOKEN}"
         commands:
           - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5_expansion.py -m 'full_model' --run-level 'full_model'
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Duplex Test"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - >-
-            pytest -s -v
-            tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
-            tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
-            -m "npu and A3 and omni"
-            --run-level full_model
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - |
-            set +e
-            pytest -s -v tests/e2e/accuracy/minicpmo_4_5/test_minicpmo_4_5.py -m "full_model and npu and A3" --run-level full_model
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/e2e/accuracy/minicpmo_4_5/results/*.json"
-            exit $$EXIT
   - group: ":card_index_dividers: TTS Model Test"
     key: nightly-tts-test-group
     depends_on: upload-nightly-pipeline

.buildkite/npu/test-npu-ready.yml

@@ -3,20 +3,22 @@ steps:
     key: ready-omni-group
     depends_on: upload-ready-pipeline
     steps:
-      - label: "Omni · MiniCPM-o 4.5 Test"
-        mirror_hardwares: a3_npu_2
+      - label: ":robot: Omni · MiniCPM-o 4.5 Test"
+        agents:
+          queue: "ascend-a3"
+          resource_class: "npu-2"
+        image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
+        plugins:
+          - kubernetes:
+              podSpecPatch:
+                imagePullSecrets:
+                  - name: swr-secret
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
+          HF_TOKEN: "${HF_TOKEN}"
         commands:
-          - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
-      - label: "Omni · MiniCPM-o 4.5 Duplex Test"
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
+          - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model' --run-level 'core_model'
 
   - group: ":card_index_dividers: TTS Model Test"
     key: ready-tts-group

.claude/skills/readme.md

@@ -1,9 +1,9 @@
-# Repository Skills for vLLM-Omni
+# Claude Skills for vLLM-Omni
 
-This directory contains repository-scale skills maintained for `vllm-omni`.
-They capture repeatable workflows for common contributor and maintainer tasks
-such as model integration, CI-aligned testing, performance optimization, and
-pull request review.
+This directory contains Claude Code skills maintained for the `vllm-omni`
+repository. These skills capture repeatable workflows for common contributor
+tasks such as model integration, pull request review, and release note
+generation.
 
 ## Directory Structure
 
@@ -14,41 +14,31 @@ include:
 - `references/`: focused reference material used by the skill
 - `scripts/`: small helper scripts used by the skill
 
-## Using the Skills
-
-Coding agents that discover repository skills can invoke the relevant skill by
-name. For other agents, point them to the skill's `SKILL.md` and ask them to
-read it before changing code. Combine a domain skill with `vllm-omni-test` when
-tests or CI coverage change, then use `precheck-pr` for the contributor's final
-self-check.
-
 ## Available Skills
 
-- [`add-diffusion-model`](add-diffusion-model/SKILL.md): guides integration of
-  a new diffusion model into `vllm-omni`
-- [`add-tts-model`](add-tts-model/SKILL.md): covers integration of new TTS
-  models and related serving workflows
-- [`diffusion-perf-opt`](diffusion-perf-opt/SKILL.md): guides diffusion model
-  performance optimization, including profiling traces, parallel strategies,
-  stage timing analysis, and benchmark-driven tuning
-- [`precheck-pr`](precheck-pr/SKILL.md): self-checks a branch before creating a
-  PR by validating title format, dead code, accuracy and performance claims,
-  and merge readiness
-- [`quantization`](quantization/SKILL.md): guides quantization method selection,
-  model integration, checkpoint loading, and quality/performance validation
-  for vLLM-Omni
-- [`review-pr`](review-pr/SKILL.md): provides a frozen-snapshot, contract-aware
-  workflow for maintainers and reviewers; contributors should use
-  `precheck-pr` for self-review
-- [`vllm-omni-npu-model-runner-upgrade`](vllm-omni-npu-upgrade/SKILL.md):
-  upgrades NPU model runners to align with the latest vllm-ascend
-  `NPUModelRunner`
-- [`vllm-omni-test`](vllm-omni-test/SKILL.md): guides generation and execution
-  of CI-aligned tests (L1–L4), pytest marker selection (`core_model` /
-  `advanced_model` / `full_model`, `omni` / `tts` / `diffusion`), Buildkite
-  wiring (`test-ready.yml`, `test-merge.yml`, `test-nightly.yml`,
-  `test-weekly.yml`), and copy-paste local plus CI-like `pytest` commands; see
-  `references/test-routing.md` for level-to-command mapping
+- `add-diffusion-model`: guides integration of a new diffusion model into
+  `vllm-omni`
+- `diffusion-perf-opt`: guides diffusion model performance optimization,
+  including profiling traces, parallel strategies, stage timing analysis, and
+  benchmark-driven tuning
+- `quantization`: guides quantization method selection, model integration,
+  checkpoint loading, and quality/performance validation for vLLM-Omni
+- `add-omni-model`: covers addition of new omni-modality model support
+- `add-tts-model`: covers integration of new TTS models and related serving
+  workflows
+- `generate-release-note`: helps prepare release notes for repository changes
+- `precheck-pr`: self-check a branch before creating a PR — validates PR title
+  format, catches dead code, verifies accuracy/perf claims, and confirms merge
+  readiness
+- `vllm-omni-test`: guides generation and execution of CI-aligned tests (L1–L4),
+  pytest marker selection (`core_model` / `advanced_model` / `full_model`,
+  `omni` / `tts` / `diffusion`), Buildkite wiring (`test-ready.yml`,
+  `test-merge.yml`, `test-nightly.yml`, `test-weekly.yml`), and copy-paste
+  local plus CI-like `pytest` commands; see `references/test-routing.md` for
+  level-to-command mapping
+- `review-pr`: provides a structured workflow for reviewing pull requests
+- `vllm-omni-npu-model-runner-upgrade`: upgrades NPU model runners to align with the
+  latest vllm-ascend NPUModelRunner
 
 ## Maintenance Guidelines
 

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

@@ -94,6 +94,7 @@ If docs and live code disagree, verify the code/tests and report the drift.
 | --- | --- |
 | [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. |
+| [config-provenance.md](references/checks/config-provenance.md) | Changed or newly load-bearing behavior reads config, CLI, environment, legacy, or default values. |
 | [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. |
@@ -152,13 +153,19 @@ contract they protect or use only the applicable evidence checks.
 Apply every category in [general-checks.md](references/process/general-checks.md) before
 lower-priority comments.
 
-For each changed value or behavior, trace:
+For each changed or newly load-bearing value or behavior, trace:
 
 ```text
 public ingress -> validation/defaulting -> producer -> transformations
   -> stage/worker/connector boundary -> final consumer -> terminal cleanup
 ```
 
+Treat unchanged context as in scope when the diff makes it authoritative for a
+new consumer. When config, CLI, environment, legacy, or default sources can
+control that value, apply
+[config-provenance.md](references/checks/config-provenance.md) and prove the
+documented source at the final sink with distinct sentinel values.
+
 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.

.claude/skills/review-pr/references/checks/config-provenance.md

@@ -0,0 +1,49 @@
+# Configuration Provenance
+
+Read this reference when changed or newly load-bearing behavior reads config,
+CLI, environment, legacy, alias, or default values. Always use it for endpoint,
+host, port, address, connector metadata, and `*_extra_config` consumers, even
+when the schema or documentation is unchanged.
+
+## Trace the source of truth
+
+For each semantic value, record one compact ledger:
+
+```text
+documented input -> parsed field -> competing sources and precedence
+  -> runtime projection/transport -> final consumer
+```
+
+- Search the exact field, environment variable, default literal, and aliases in
+  code, tests, docs, examples, and deployment files.
+- Treat unchanged producers and context lines as review scope when the diff
+  starts relying on them or makes their output authoritative.
+- Resolve the intended precedence from active branch-local docs, enforced
+  code/tests, and compatibility policy. Report a documented input that is
+  silently ignored or reinterpreted at a live sink.
+- Check every supported construction path and feature-off behavior without
+  inventing parity for unsupported paths.
+
+## Require discriminating evidence
+
+Give every competing source a distinct value so the test reveals which source
+wins. Prefer non-default sentinels; for example:
+
+```text
+documented config port = 25301
+environment/default port = 8998
+expected final endpoint = http://10.0.0.8:25301
+```
+
+Assert the final URL, connection target, runtime argument, or other live sink,
+not only an intermediate object. A test that changes the environment value to
+the expected configured value proves formatting, not configuration propagation.
+For a bug fix, show the discriminating test fails on the frozen base and passes
+on the reviewed head when the environment permits execution.
+
+## Finding bar
+
+A supported non-default value reaching the wrong endpoint, device, topology, or
+runtime behavior is a correctness or compatibility finding. A missing
+discriminating test alone is a validation gap unless repository policy requires
+that regression coverage for the change.

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

@@ -16,6 +16,9 @@ were reverted or broken. Check:
   instead of the changed behavior being mocked away;
 - fakes preserve relevant types, MRO, shapes, devices, async behavior, and
   lifecycle transitions;
+- configuration tests give competing config, CLI, environment, legacy, and
+  default sources distinct non-default values and assert the final consumer;
+  setting only the source read by the implementation does not prove precedence;
 - seeds, ordering, timing, synchronization, external services, and numeric
   tolerances are deterministic or explicitly controlled;
 - normal, invalid, boundary, feature-off, failure/cancellation, and regression

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

@@ -15,6 +15,9 @@ and [design documents](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/
 - Trace each changed value through public ingress, validation/defaulting,
   producer, transformations, process or device boundaries, final consumer, and
   terminal cleanup.
+- Treat unchanged code as in scope when the diff makes its value newly
+  load-bearing for a changed consumer; validate that value's origin and contract
+  rather than reviewing only added lines.
 - Check every applicable sync/async, offline/online, streaming/non-streaming,
   feature-off, topology, and compatibility path without demanding unsupported
   modes merely for symmetry.
@@ -123,7 +126,9 @@ 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.
+Anchor each finding to the exact `path:line` that causes the behavior; it may be
+unchanged when the diff makes it newly load-bearing, in which case name the
+changed call path that brings it into scope. Include the trigger, 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

@@ -166,6 +166,10 @@ 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.
 
+When the root cause is an unchanged line made newly load-bearing by the diff,
+cite it in the consolidated review body instead of moving the comment to an
+unrelated changed line merely to make it inline.
+
 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

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

@@ -50,6 +50,7 @@ compatibility changes.
 | --- | --- | --- |
 | 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 |
+| Config/CLI/environment/default precedence; endpoint, host, port, address, connector metadata, or `*_extra_config` | [config-provenance.md](../checks/config-provenance.md) | None |
 | 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 |

.github/CODEOWNERS

@@ -1,11 +1,6 @@
 # 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
@@ -26,10 +21,25 @@
 # CI
 /.buildkite/ @yenuo26 @congw729 @NickCao
 
-# ComfyUI / external apps
-/apps/ @fhfuih @alex-jw-brooks
+# 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
 
-# Benchmarks (out-of-tree)
+# 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/accuracy/ @david6666666
 /benchmarks/build_dataset/ @linyueqian @yuanheng-zhao
 /benchmarks/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @xuechendi
@@ -37,112 +47,20 @@
 /benchmarks/glm_image/ @princepride @JaredforReal
 /benchmarks/tts/ @linyueqian @ZeldaHuang @princepride @Sy0307 @gcanlin
 
-# =====================================================================
-# Module design ownership (docs/design/module/*.md)
-# Each section header cites the source design doc.
-# =====================================================================
-
-# Autoregressive runtime — docs/design/module/ar_runtime.md
-/vllm_omni/core/ @tzhouam @yinpeiqi @fake0fan @Sy0307 @Gaohan123
-/vllm_omni/worker/ @tzhouam @yinpeiqi @fake0fan @Sy0307 @Gaohan123
-
-# 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
-
-# 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
-
-# Observability — docs/design/module/observability.md
-/vllm_omni/metrics/ @lishunyang12 @vraiti
-
-# Profiling — docs/design/module/profiling.md
+# Usability and Observability
+/vllm_omni/deploy/ @tzhouam @lishunyang12
+/vllm_omni/metrics/ @lishunyang12
 /vllm_omni/profiler/ @gcanlin
 
-# Benchmarking (in-tree) — docs/design/module/benchmarking.md
-/vllm_omni/benchmarks/ @alex-jw-brooks @Bounty-hunter
+# ComfyUI
+/apps/ @fhfuih @alex-jw-brooks
 
-# LoRA (no dedicated design doc; ownership intentionally narrowed)
-/vllm_omni/lora/ @SamitHuang @wtomin
+# Large Scale Serving
+/vllm_omni/distributed/ @princepride @yuanheng-zhao @xuechendi @natureofnature @fake0fan
 
-# Transformers utils (related path only in design docs; preserves prior ownership)
-/vllm_omni/transformers_utils/ @tzhouam @yuanheng-zhao
+# Quantization and configuration
+/vllm_omni/config/ @lishunyang12 @alex-jw-brooks
+/vllm_omni/quantization/ @david6666666 @Isotr0py @lishunyang12
 
-# =====================================================================
-# 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
+# Hardware plugins and accelerators
+/vllm_omni/platforms/ @gcanlin @tjtanaa @xuechendi

.pre-commit-config.yaml

@@ -66,10 +66,7 @@ repos:
       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
+      files: ^vllm_omni/entrypoints/openai/(serving_speech\.py|tts_adapters/__init__\.py)$
 
     # Keep `suggestion` last
     - id: suggestion

benchmarks/tts/README.md

@@ -139,34 +139,6 @@ python benchmarks/tts/bench_tts.py \
     --output-dir ./results
 ```
 
-#### Fixed IndexTTS 2.5 performance sweep
-
-IndexTTS 2.5 is registered in `model_configs.yaml` like the other TTS models.
-Use `--served-model-name` when the server was launched from a local native
-bundle instead of the registry key. The command below reproduces the acceptance
-workload: Seed-TTS Eval EN, `n=500`, concurrency `4/8/16/32`, five warmups, and
-dataset seed 0.
-
-```bash
-python benchmarks/tts/bench_tts.py \
-    --model IndexTeam/IndexTTS-2.5 \
-    --served-model-name /path/to/indextts-2.5 \
-    --task voice_clone --locale en \
-    --dataset-path /path/to/seedtts_testset \
-    --host 127.0.0.1 --port 8092 \
-    --concurrency 4 8 16 32 \
-    --num-prompts 500 --num-warmups 5 \
-    --output-dir ./results/indextts2_5 \
-    -- \
-    --tokenizer /path/to/indextts-2.5/qwen0.6bemo4-merge \
-    --seed 0 --metric-percentiles 50,95,99 --disable-tqdm --save-detailed
-```
-
-The wrapper benchmarks an already-running server. For reproducible quality
-comparisons, add `--request-seed 42`; production-performance runs should omit
-it. The trailing `--seed 0` controls Seed-TTS row selection rather than model
-sampling.
-
 ### 4. Plot a sweep
 
 ```bash

benchmarks/tts/bench_tts.py

@@ -84,17 +84,12 @@ def build_bench_args(
     result_filename: str | None,
     extra_cli_args: list[str],
     output_len: int | None = None,
-    served_model_name: str | None = None,
-    num_warmups: int = 2,
-    request_seed: int | None = None,
 ) -> list[str]:
     """Build the ``vllm bench serve --omni`` command for one (task, concurrency) run."""
     dataset_name = _TASK_TO_DATASET[task]
     backend: str = model_cfg["backend"]
     endpoint: str = model_cfg["endpoint"]
-    task_extra_body: dict[str, Any] = dict((model_cfg.get("task_extra_body") or {}).get(task) or {})
-    if request_seed is not None:
-        task_extra_body["seed"] = request_seed
+    task_extra_body: dict[str, Any] = (model_cfg.get("task_extra_body") or {}).get(task) or {}
 
     # Resolve dataset path
     if dataset_path:
@@ -114,7 +109,7 @@ def build_bench_args(
         "--port",
         str(port),
         "--model",
-        served_model_name or model,
+        model,
         "--backend",
         backend,
         "--endpoint",
@@ -124,7 +119,7 @@ def build_bench_args(
         "--num-prompts",
         str(num_prompts),
         "--num-warmups",
-        str(num_warmups),
+        "2",
         "--percentile-metrics",
         "ttft,e2el,audio_rtf,audio_ttfp,audio_duration,audio_underrun",
     ]
@@ -157,8 +152,7 @@ def build_bench_args(
         if result_filename:
             cmd += ["--result-filename", result_filename]
 
-    passthrough = extra_cli_args[1:] if extra_cli_args[:1] == ["--"] else extra_cli_args
-    cmd += passthrough
+    cmd += extra_cli_args
     return cmd
 
 
@@ -231,12 +225,6 @@ def main() -> None:
     parser.add_argument(
         "--model", required=True, help="HuggingFace model ID (e.g. Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice)"
     )
-    parser.add_argument(
-        "--served-model-name",
-        default=None,
-        help="Model name/path accepted by the running server. Use this when --model selects a registry entry "
-        "but the server was launched from a local bundle path.",
-    )
     parser.add_argument("--task", default="all", help="Task type: voice_clone | default_voice | voice_design | all")
     parser.add_argument("--locale", default="en", choices=["en", "zh"])
     parser.add_argument("--concurrency", type=int, nargs="+", default=[1, 4], metavar="N")
@@ -248,13 +236,6 @@ def main() -> None:
         metavar="N",
         help="Number of prompts per run. If one value, applied to all concurrency levels.",
     )
-    parser.add_argument("--num-warmups", type=int, default=2, help="Warmup requests before each measured run")
-    parser.add_argument(
-        "--request-seed",
-        type=int,
-        default=None,
-        help="Optional model sampling seed added to every request body for reproducible quality runs",
-    )
     parser.add_argument(
         "--dataset-path", default=None, help="Root of seed-tts-eval dataset (required for voice_clone/default_voice)"
     )
@@ -275,9 +256,6 @@ def main() -> None:
     parser.add_argument("extra", nargs=argparse.REMAINDER, help="Extra args passed directly to vllm bench serve")
     args = parser.parse_args()
 
-    if args.num_warmups < 0:
-        parser.error("--num-warmups cannot be negative")
-
     model_configs = load_model_configs(Path(args.model_configs))
     if args.model not in model_configs:
         known = "\n  ".join(model_configs.keys())
@@ -330,9 +308,6 @@ def main() -> None:
                 result_filename=result_filename,
                 extra_cli_args=args.extra or [],
                 output_len=args.output_len,
-                served_model_name=args.served_model_name,
-                num_warmups=args.num_warmups,
-                request_seed=args.request_seed,
             )
             result = run_one_benchmark(cmd)
             if result is not None:

benchmarks/tts/model_configs.yaml

@@ -7,17 +7,6 @@
 # is tracked here.
 
 models:
-  IndexTeam/IndexTTS-2.5:
-    supported_tasks: [voice_clone]
-    backend: openai-audio-speech
-    endpoint: /v1/audio/speech
-    trust_remote_code: true
-    task_extra_body:
-      voice_clone:
-        extra_params:
-          lang: en
-          text_normalization: true
-
   # -CustomVoice checkpoints lack speaker_encoder weights, so voice_clone is
   # NOT supported (an attempt raises ValueError from _extract_speaker_embedding
   # at model runtime).  Use -Base for voice_clone.

docker/Dockerfile.ci

@@ -1,24 +1,7 @@
-# Target vllm version: v0.27.0 (releases/v0.27.0 branch).
+# Target vllm version: v0.26.0 (releases/v0.26.0 branch).
 # Keep VLLM_BASE_TAG aligned with the target vLLM release on every rebase.
-#
-# Release-boundary form: there is no precompiled-wheel pin here, because the
-# base image already ships exactly the target vLLM. Everything the runtime
-# needs — torch, flashinfer, nvJitLink, numpy — comes from that image as one
-# self-consistent set.
-#
-# This block reappears only when the rebase targets a vLLM commit that is NOT a
-# released tag. During the 0.27 rebase, targeting v0.27.0rc1 on top of the
-# v0.26.0 base image required reinstalling vLLM from wheels.vllm.ai and then
-# hand-repairing the fallout: pinning torch ahead of flashinfer (installing it
-# after bound flashinfer's TVM FFI runtime to the old torch and aborted engine
-# core init), registering libnvJitLink.so.13 with ldconfig, and re-pinning numpy
-# under numba's ceiling. All of it was compensation for a base image and a vLLM
-# that disagreed. At a real release boundary they agree, so none of it is
-# needed. If you pin an untagged commit again, restore the reinstall block —
-# agent/tasks/20_update_wheel_url.sh fails the run rather than letting the
-# Dockerfile silently ship the wrong vLLM.
 ARG VLLM_BASE_IMAGE=vllm/vllm-openai
-ARG VLLM_BASE_TAG=v0.27.0
+ARG VLLM_BASE_TAG=v0.26.0
 
 # We use registry-based layer caching for the dependencies,
 # where the tag is determined based on the hash of the contents

docker/Dockerfile.npu.ci

@@ -45,7 +45,6 @@ RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
       "hyperpyyaml>=1.2.0" \
       "onnx>=1.16.0" \
       "librosa>=0.10.0" \
-      "datasets>=3.0.0" \
       --index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
       --trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
       --default-timeout=60 && \

docker/Dockerfile.npu.ci.a3

@@ -46,7 +46,6 @@ RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
       "onnx>=1.16.0" \
       "librosa>=0.10.0" \
       "torchmetrics>=1.9.0" \
-      "datasets>=3.0.0" \
       --index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
       --trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
       --default-timeout=60 && \

docker/Dockerfile.xpu

@@ -88,7 +88,7 @@ ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
 ENV UV_INDEX_STRATEGY="unsafe-best-match"
 ENV UV_LINK_MODE="copy"
 
-ARG VLLM_VERSION=v0.27.0
+ARG VLLM_VERSION=v0.26.0
 RUN git clone -b ${VLLM_VERSION} https://github.com/vllm-project/vllm
 WORKDIR /workspace/vllm
 
@@ -108,7 +108,7 @@ ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
 
 RUN --mount=type=cache,target=/root/.cache/uv \
     uv pip uninstall triton triton-xpu && \
-    uv pip install triton-xpu==3.7.2 && \
+    uv pip install triton-xpu==3.7.1 && \
     uv pip install --no-build-isolation --no-deps .
 
 CMD ["/bin/bash"]
@@ -144,13 +144,12 @@ WORKDIR /workspace/vllm-omni
 COPY . .
 
 ENV VLLM_OMNI_TARGET_DEVICE=xpu
-# Keep the upstream oneCCL packages paired with the XPU torch runtime.
 RUN --mount=type=cache,target=/root/.cache/uv \
     uv pip install --no-build-isolation \
     --extra-index-url https://mirrors.ustc.edu.cn/pypi/simple/ \
     ".[dev]" && \
-    uv pip uninstall triton && \
-    uv pip install triton-xpu==3.7.2 --reinstall
+    uv pip uninstall triton oneccl oneccl-devel && \
+    uv pip install triton-xpu==3.7.1 --reinstall
 
 FROM vllm-omni AS vllm-omni-openai
 

docs/.nav.yml

@@ -16,21 +16,31 @@ 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
-      - Speech-To-Video: user_guide/examples/offline_inference/speech_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
       - 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
-      - Speech-To-Video: user_guide/examples/online_serving/speech_to_video.md
-      - Text-To-Image: user_guide/examples/online_serving/text_to_image.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
+      - Text-To-Image: user_guide/examples/online_serving/text_to_image.md
       - Text-To-Video: user_guide/examples/online_serving/text_to_video.md
   - General:
     - usage/*
@@ -40,30 +50,16 @@ nav:
   - Models:
     - models/supported_models.md
   - Features:
-    - Overview: features/README.md
-    - Runtime and Stage Execution:
-      - Execution Modes and Streaming: user_guide/diffusion/execution_modes.md
-      - Sleep Mode: features/sleep_mode.md
-    - Quantization:
-      - Overview: user_guide/quantization/overview.md
-      - Online Quantization: user_guide/quantization/online.md
-      - Quantized KV Cache: user_guide/quantization/quantized_kvcache.md
-      - FP8 W8A8: user_guide/quantization/fp8.md
-      - Int8 W8A8: user_guide/quantization/int8.md
-      - BitsAndBytes W4: user_guide/quantization/bitsandbytes.md
-      - MXFP8 W8A8: user_guide/quantization/mxfp8.md
-      - MXFP4 W4A4: user_guide/quantization/mxfp4.md
-      - ModelOpt: user_guide/quantization/modelopt.md
-      - AutoRound: user_guide/quantization/autoround.md
-      - msModelSlim: user_guide/quantization/msmodelslim.md
-    - Diffusion Acceleration:
-      - Overview and Compatibility:
-        - Overview: user_guide/diffusion_features.md
-        - Feature Compatibility: user_guide/feature_compatibility.md
-      - CPU Offloading: user_guide/diffusion/cpu_offload.md
+    - Sleep Mode: features/sleep_mode.md
+    - Diffusion Features:
+      - Overview: user_guide/diffusion_features.md
+      - Feature Compatibility: user_guide/feature_compatibility.md
+      - Regional Compilation: user_guide/diffusion/regional_compilation.md
       - Cache Acceleration:
         - TeaCache: user_guide/diffusion/cache_acceleration/teacache.md
         - Cache-DiT: user_guide/diffusion/cache_acceleration/cache_dit.md
+      - Attention Backends: user_guide/diffusion/attention_backends.md
+      - Frame Interpolation: user_guide/diffusion/frame_interpolation.md
       - Parallelism:
         - Overview: user_guide/diffusion/parallelism/overview.md
         - CFG Parallel: user_guide/diffusion/parallelism/cfg_parallel.md
@@ -72,15 +68,23 @@ nav:
         - Sequence Parallel: user_guide/diffusion/parallelism/sequence_parallel.md
         - Tensor Parallel: user_guide/diffusion/parallelism/tensor_parallel.md
         - VAE Parallelism: user_guide/diffusion/parallelism/vae_parallelism.md
-      - Attention Backends: user_guide/diffusion/attention_backends.md
-      - Regional Compilation: user_guide/diffusion/regional_compilation.md
-      - Frame Interpolation: user_guide/diffusion/frame_interpolation.md
-      - Startup and Loading: user_guide/diffusion/startup_and_loading.md
+      - CPU Offloading: user_guide/diffusion/cpu_offload.md
       - LoRA: user_guide/diffusion/lora.md
-    - Experimental:
-      - Session State Manager: features/session_state_manager.md
-  - Integrations:
-    - Custom Diffusion Pipeline: features/custom_pipeline.md
+      - Custom Pipeline: features/custom_pipeline.md
+      - Execution Modes: user_guide/diffusion/execution_modes.md
+    - Quantization:
+      - Quantization: user_guide/quantization/overview.md
+      - Online Quantization: user_guide/quantization/online.md
+      - Quantized KV Cache: user_guide/quantization/quantized_kvcache.md
+      - FP8 W8A8: user_guide/quantization/fp8.md
+      - Int8 W8A8: user_guide/quantization/int8.md
+      - BitsAndBytes W4: user_guide/quantization/bitsandbytes.md
+      - MXFP8 W8A8: user_guide/quantization/mxfp8.md
+      - MXFP4 W4A4: user_guide/quantization/mxfp4.md
+      - ModelOpt: user_guide/quantization/modelopt.md
+      - GGUF: user_guide/quantization/gguf.md
+      - AutoRound: user_guide/quantization/autoround.md
+      - msModelSlim: user_guide/quantization/msmodelslim.md
     - ComfyUI: features/comfyui.md
   - Fault Tolerance:
     - Failure Modes: user_guide/fault_injection_reliability_matrix.md
@@ -114,7 +118,6 @@ nav:
           - Shared Memory Connector: design/feature/omni_connectors/shared_memory_connector.md
           - Yuanrong Store Connector: design/feature/omni_connectors/yuanrong_connector.md
           - Yuanrong Transfer Engine Connector: design/feature/omni_connectors/yuanrong_transfer_engine_connector.md
-      - Quantization: design/feature/quantization.md
       - Diffusion Acceleration:
         - Parallelism:
           - CFG-Parallel: design/feature/cfg_parallel.md
@@ -124,8 +127,9 @@ nav:
           - Sequence Parallel: design/feature/sequence_parallel.md
           - Tensor Parallel: design/feature/tensor_parallel.md
           - VAE Patch Parallelism: design/feature/vae_parallel.md
-        - Attention Optimization:
+        - Attention Backends:
           - Skip-Softmax: design/feature/skip_softmax.md
+        - Quantization: design/feature/quantization.md
         - Cache-DiT: design/feature/cache_dit.md
         - TeaCache: design/feature/teacache.md
         - Diffusion Continuous Batching: design/feature/diffusion_continuous_batching.md

docs/contributing/README.md

@@ -76,47 +76,6 @@ Please refer to the [test instructions](./ci/test_execution_guide.md) for detail
 !!! warning
     Currently, not all unit tests pass when run on CPU platforms. If you don't have access to a GPU platform to run unit tests locally, rely on the continuous integration system to run the tests for now.
 
-### Using repository skills with coding agents
-
-vLLM-Omni maintains [repository-scale skills](https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills) for common coding, testing, performance, and review workflows. These skills capture repository-specific structure, validation requirements, and evidence standards that a general coding agent may not know.
-
-If your coding agent discovers repository skills automatically, ask it to use the relevant skill by name. Otherwise, point it to the linked `SKILL.md` and ask it to read the file before changing code. Skills can be combined: use a domain skill for the implementation, `vllm-omni-test` for test and CI decisions, and `precheck-pr` before opening the pull request.
-
-| Task | Repository skill |
-| --- | --- |
-| Add or extend a diffusion model | [`add-diffusion-model`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/add-diffusion-model/SKILL.md) |
-| Add or extend a text-to-speech model | [`add-tts-model`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/add-tts-model/SKILL.md) |
-| Add, select, or debug quantization | [`quantization`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/quantization/SKILL.md) |
-| Diagnose or optimize diffusion performance | [`diffusion-perf-opt`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/diffusion-perf-opt/SKILL.md) |
-| Upgrade an NPU model runner | [`vllm-omni-npu-model-runner-upgrade`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/vllm-omni-npu-upgrade/SKILL.md) |
-| Add a regression test, choose L1-L4 coverage, or wire Buildkite | [`vllm-omni-test`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/vllm-omni-test/SKILL.md) |
-| Self-check a branch before opening a pull request | [`precheck-pr`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/precheck-pr/SKILL.md) |
-| Perform a maintainer or reviewer review of an existing pull request or local branch | [`review-pr`](https://github.com/vllm-project/vllm-omni/blob/main/.claude/skills/review-pr/SKILL.md) |
-
-Use the following workflow when collaborating with a coding agent:
-
-1. **Ground the task.** Provide the issue, RFC, or design document that defines the expected behavior. Ask the agent to state its assumptions and identify the affected module or feature contracts before editing code.
-2. **Select the narrowest applicable skills.** Start with the domain skill that owns the change. Add `vllm-omni-test` whenever production behavior or tests change. For a bug fix, ask for the smallest reproducer and a regression test tied to the original symptom.
-3. **Require executable evidence.** Ask the agent to run the narrowest relevant checks and report the exact commands and results. It must identify tests it could not run because of unavailable hardware, model weights, credentials, or dependencies; an unrun check is not a pass.
-4. **Inspect the resulting diff.** Confirm that the implementation stays within the issue or RFC, does not overwrite unrelated work, and includes the required tests, documentation, and benchmark or accuracy evidence.
-5. **Run the pre-submit workflow.** Use `precheck-pr`, then run the applicable local tests and pre-commit hooks before opening the pull request.
-
-For example:
-
-```text
-Use add-diffusion-model and vllm-omni-test to implement the linked issue.
-Read the relevant design documents first, keep the change within the issue,
-and report every test command, result, and hardware validation gap.
-```
-
-```text
-Use vllm-omni-test to turn this bug reproducer into the smallest deterministic
-regression test. Prefer L1 CPU coverage; if the failure requires real weights
-or serving, explain the required L2/L3 environment and provide the exact command.
-```
-
-Repository skills guide the agent, but they do not replace contributor judgment, the accepted issue or RFC, required test evidence, or maintainer review. Review all generated changes before submitting them.
-
 ## Issues
 
 If you encounter a bug or have a feature request, please search existing issues first to see if it has already been reported. If not, please file a new issue, providing as much relevant information as possible.

docs/design/index.md

@@ -11,10 +11,6 @@ in the active navigation.
 
 ## Feature Design Documents
 
-For user-facing configuration and current compatibility, see the
-[Features overview](../features/README.md). A design document defines an
-implementation contract; it is not, by itself, a general support claim.
-
 ### Runtime and stage execution
 
 - [Disaggregated Inference](feature/disaggregated_inference.md)
@@ -34,10 +30,6 @@ implementation contract; it is not, by itself, a general support claim.
 - [Yuanrong Store Connector](feature/omni_connectors/yuanrong_connector.md)
 - [Yuanrong Transfer Engine Connector](feature/omni_connectors/yuanrong_transfer_engine_connector.md)
 
-### Quantization
-
-- [Quantization](feature/quantization.md)
-
 ### Diffusion acceleration
 
 #### Parallelism
@@ -50,14 +42,14 @@ implementation contract; it is not, by itself, a general support claim.
 - [Tensor Parallel](feature/tensor_parallel.md)
 - [VAE Patch Parallelism](feature/vae_parallel.md)
 
-#### Attention optimization
-
-The [Diffusion Attention Backends](../user_guide/diffusion/attention_backends.md)
-guide lists all selectable backends and their platform defaults. Skip-Softmax
-is the backend-related optimization with a standalone feature-design contract:
+#### Attention Backends
 
 - [Skip-Softmax](feature/skip_softmax.md)
 
+#### Quantization
+
+- [Quantization](feature/quantization.md)
+
 - [Cache-DiT](feature/cache_dit.md)
 - [TeaCache](feature/teacache.md)
 - [Diffusion Continuous Batching](feature/diffusion_continuous_batching.md)

docs/design/module/ar_runtime.md

@@ -7,7 +7,6 @@ owners:
   - "@yinpeiqi"
   - "@fake0fan"
   - "@Sy0307"
-  - "@Gaohan123"
 primary_code_paths:
   - vllm_omni/core/**
   - vllm_omni/worker/**

docs/design/module/benchmarking.md

@@ -4,7 +4,6 @@ kind: module
 status: draft
 owners:
   - "@alex-jw-brooks"
-  - "@Bounty-hunter"
 primary_code_paths:
   - vllm_omni/benchmarks/**
   - vllm_omni/entrypoints/cli/benchmark/**

docs/design/module/cache_management.md

@@ -5,7 +5,6 @@ status: draft
 owners:
   - "@Isotr0py"
   - "@princepride"
-  - "@SamitHuang"
 primary_code_paths:
   - vllm_omni/diffusion/cache/**
 related_code_paths:

docs/design/module/diffusion/diffusion_model_integration.md

@@ -3,10 +3,9 @@ title: Diffusion Model Integration
 kind: module
 status: draft
 owners:
-  - "@fhfuih"
-  - "@Bounty-hunter"
+  - "@Isotr0py"
   - "@wtomin"
-  - "@RuixiangMa"
+  - "@ZJY0516"
 primary_code_paths:
   - vllm_omni/diffusion/models/**
   - vllm_omni/diffusion/model_loader/**

docs/design/module/diffusion/diffusion_runtime.md

@@ -6,7 +6,6 @@ owners:
   - "@Isotr0py"
   - "@princepride"
   - "@SamitHuang"
-  - "@fhfuih"
 primary_code_paths:
   - vllm_omni/diffusion/sched/**
   - vllm_omni/diffusion/executor/**

docs/design/module/diffusion/offloader.md

@@ -4,8 +4,7 @@ kind: module
 status: draft
 owners:
   - "@yuanheng-zhao"
-  - "@david6666666"
-  - "@lishunyang12"
+  - "@Isotr0py"
 primary_code_paths:
   - vllm_omni/diffusion/offloader/**
 related_code_paths:

docs/design/module/diffusion/parallelism.md

@@ -6,7 +6,6 @@ owners:
   - "@princepride"
   - "@yuanheng-zhao"
   - "@xuechendi"
-  - "@Bounty-hunter"
 primary_code_paths:
   - vllm_omni/diffusion/distributed/**
   - vllm_omni/diffusion/attention/parallel/**

docs/design/module/entrypoints.md

@@ -6,7 +6,6 @@ architecture_state: current-plus-in-flight
 owners:
   - "@alex-jw-brooks"
   - "@linyueqian"
-  - "@NickCao"
 document_stewards:
   - "@hsliuustc0106"
   - "@Gaohan123"

docs/design/module/execution_platforms.md

@@ -8,15 +8,8 @@ owners:
   - "@xuechendi"
 primary_code_paths:
   - vllm_omni/platforms/**
+related_code_paths:
   - 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

docs/design/module/input_output_modality_contracts.md

@@ -6,8 +6,6 @@ architecture_state: current
 owners:
   - "@Sy0307"
   - "@amy-why-3459"
-  - "@Gaohan123"
-  - "@alex-jw-brooks"
 document_stewards:
   - "@hsliuustc0106"
   - "@Gaohan123"

docs/design/module/model_integration.md

@@ -9,14 +9,6 @@ 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/**

docs/design/module/observability.md

@@ -4,7 +4,6 @@ kind: module
 status: draft
 owners:
   - "@lishunyang12"
-  - "@vraiti"
 primary_code_paths:
   - vllm_omni/metrics/**
 related_code_paths:

docs/features/README.md

@@ -1,67 +0,0 @@
-# Features
-
-Use this section to choose and configure vLLM-Omni runtime and optimization
-features. The navigation follows the active
-[Feature Design](../design/index.md#feature-design-documents) taxonomy whenever
-an implementation contract has a user-facing workflow.
-
-!!! note "User guides, design documents, and recipes"
-
-    User guides explain how to enable a feature and where it is supported.
-    Design documents define internal contracts and do not, by themselves,
-    imply general or production support. For model-specific launch flags and
-    hardware requirements, use the linked examples and validated recipes from
-    [Supported Models](../models/supported_models.md).
-
-## Runtime and Stage Execution
-
-| Goal | User guide | Related design contract |
-| --- | --- | --- |
-| Choose serial, batched, step-wise, or streaming diffusion execution | [Execution Modes and Streaming](../user_guide/diffusion/execution_modes.md) | [Diffusion Continuous Batching](../design/feature/diffusion_continuous_batching.md), [Async Diffusion Output](../design/feature/async_diffusion_output.md) |
-| Reclaim stage memory without restarting the server | [Sleep Mode](sleep_mode.md) | Runtime lifecycle behavior is documented in the user guide |
-
-Some runtime designs are deliberately not promoted as standalone User Guide
-features yet:
-
-- [Disaggregated Inference](../design/feature/disaggregated_inference.md) and
-  [OmniConnector implementations](../design/index.md#communication) describe
-  topology and transport contracts. Practical deployment configuration remains
-  under [Pipeline and deploy configurations](../configuration/stage_configs.md).
-- [Async Chunk](../design/feature/async_chunk.md) and
-  [Async Omni Output Materialization](../design/feature/omni_async_output_materialization.md)
-  are model- and pipeline-dependent. Use the selected model's deploy
-  configuration and recipe for the supported settings.
-- [Automatic Prefix Caching](../design/feature/prefix_caching.md) remains a
-  design-level contract until its user-facing configuration and compatibility
-  surface is consolidated.
-
-## Quantization
-
-Quantization is a cross-model feature rather than a diffusion-only
-optimization. The unified [`quantization_config` guide](../user_guide/quantization/overview.md)
-covers diffusion-only models, multi-stage omni/TTS models, and multi-stage
-diffusion models. Its [design contract](../design/feature/quantization.md)
-defines the shared configuration and backend extension points.
-
-## Diffusion Acceleration
-
-| Goal | User guide | Related design contract |
-| --- | --- | --- |
-| Compare acceleration methods and supported combinations | [Overview](../user_guide/diffusion_features.md), [Feature Compatibility](../user_guide/feature_compatibility.md) | [Diffusion acceleration designs](../design/index.md#diffusion-acceleration) |
-| Move weights between host and device memory | [CPU Offloading](../user_guide/diffusion/cpu_offload.md) | [Distributed Layerwise Offload](../design/feature/distributed_layerwise_offload.md) |
-| Reuse denoising computation | [Cache Acceleration](../user_guide/diffusion/cache_acceleration/cache_dit.md) | [Cache-DiT](../design/feature/cache_dit.md), [TeaCache](../design/feature/teacache.md) |
-| Distribute diffusion work across devices | [Parallelism](../user_guide/diffusion/parallelism/overview.md) | [Parallelism designs](../design/index.md#parallelism) |
-| Select dense, sparse, or quantized attention paths | [Attention Backends](../user_guide/diffusion/attention_backends.md) | [Skip-Softmax](../design/feature/skip_softmax.md) |
-| Compile repeated diffusion regions | [Regional Compilation](../user_guide/diffusion/regional_compilation.md) | User-facing optimization guide |
-| Add generated video frames | [Frame Interpolation](../user_guide/diffusion/frame_interpolation.md) | User-facing extension guide |
-| Reduce diffusion model startup time | [Startup and Loading](../user_guide/diffusion/startup_and_loading.md) | User-facing loading guide |
-| Apply diffusion adapters | [LoRA](../user_guide/diffusion/lora.md) | User-facing extension guide |
-
-The [Pipeline Parallelism guide](../user_guide/diffusion/parallelism/pipeline_parallel.md)
-remains available by direct link, but it is not promoted in the primary User
-Guide navigation until its user-facing support and placement are settled.
-
-## Experimental
-
-[Session State Manager](session_state_manager.md) is opt-in and experimental.
-Its APIs and compatibility may change without notice.

docs/mkdocs/hooks/generate_argparse.py

@@ -123,7 +123,6 @@ def extract_omni_serve_subparser_init():
                         "TrackingNamespace": None,  # type annotation only
                         "make_arg_parser": lambda parser: parser,  # no-op for doc
                         "_ensure_vllm_platform": lambda: None,  # no-op for doc
-                        "_nonneg_finite_float": float,
                         "VLLM_SUBCMD_PARSER_EPILOG": "",
                         "logger": logger,
                         "DummySubparsers": DummySubparsers,

docs/mkdocs/hooks/generate_examples.py

@@ -24,23 +24,6 @@ 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:
@@ -63,13 +46,6 @@ 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",
@@ -364,21 +340,22 @@ def update_nav_file(examples: list[Example]):
             examples_by_category[category] = []
         examples_by_category[category].append(example)
 
-    def category_items(category: str) -> list[dict[str, str]]:
-        items = []
-        for example in sorted(examples_by_category[category], key=lambda e: e.path.stem):
+    # Build the new Examples section - start with preserved items
+    examples_section = preserved_items.copy()
+
+    # Add examples grouped by category, sorted by category name
+    for category in sorted(examples_by_category.keys()):
+        category_examples = sorted(examples_by_category[category], key=lambda e: e.path.stem)
+        category_items = []
+        for example in category_examples:
             doc_path = EXAMPLE_DOC_DIR / example.category / f"{example.path.stem}.md"
             rel_path = doc_path.relative_to(ROOT_DIR / "docs")
-            items.append({example.nav_title: rel_path.as_posix()})
-        return items
+            category_items.append({example.nav_title: rel_path.as_posix()})
 
-    # Build the new Examples section - start with preserved items.
-    examples_section = preserved_items.copy()
-    for category in sorted(examples_by_category.keys()):
-        items = category_items(category)
-        if items:
+        if category_items:
+            # Format category name (e.g., "offline_inference" -> "Offline Inference")
             category_title = fix_case(category.replace("_", " ").title())
-            examples_section.append({category_title: items})
+            examples_section.append({category_title: category_items})
 
     # Update the nav structure
     nav_list[user_guide_idx]["User Guide"][examples_idx]["Examples"] = examples_section
@@ -413,8 +390,6 @@ 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

@@ -17,95 +17,84 @@ th {
 }
 </style>
 
-| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU | Recipe |
-|--------------|--------|-------------------|------------|---------|-----|-----------|--------|
-| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen3-Omni.md) |
-| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ |   |   |   | — |
-| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | | — |
-| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | | — |
-| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen-Image) |
-| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen-Image-2512.md) |
-| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | | — |
-| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | | — |
-| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ |   |   |   | — |
-| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | | — |
-| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | | — |
-| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2I, T2V, TI2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | | — |
-| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | ✅︎ | | | [Published](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3) |
-| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | | — |
-| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | | — |
-| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `LongCatVideoAvatarPipeline` | LongCat-Video-Avatar-1.5 A2V/AI2V (native single-speaker and multi-speaker AI2V/AVC) | `meituan-longcat/LongCat-Video-Avatar-1.5` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/meituan-longcat/LongCat-Video-Avatar-1.5.md) |
-| `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` | ✅︎ | | | | — |
-| `IndexTTS25TalkerForConditionalGeneration` | IndexTTS-2.5 | native `checkpoints/` bundle | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/IndexTeam/IndexTTS-2_5.md) |
-| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | | — |
-| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | | — |
-| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | | — |
-| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | | — |
-| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | | — |
-| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | | — |
-| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | | — |
-| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | | — |
-| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | | — |
-| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | | — |
-|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | | — |
-| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | | — |
-| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | | — |
-
-The `Recipe` column links the corresponding deployment recipe. `Published` is
-preferred when a corresponding `recipes.vllm.ai` page exists; otherwise the
-link points to the repository recipe. `—` means that no recipe link has been
-added for that model row yet.
-
-For rows with an audited recipe link, the hardware checkmarks reflect hardware
-explicitly documented in that recipe. Other rows retain the implementation
-support metadata until their recipe is audited.
+| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU |
+|--------------|--------|-------------------|------------|---------|-----|-----------|
+| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ |   |   |   |
+| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ |
+| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | |
+| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | |
+| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | |
+| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | |
+| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ |   |   |   |
+| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | |
+| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | |
+| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | |
+| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | | | |
+| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | |
+| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | |
+| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ |
+| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | |
+| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ |
+| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ |
+| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | |
+| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | |
+| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | |
+| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | |
+| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | |
+| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ |
+| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ |
+| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ |
+| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ |
+| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | |
+| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | |
+| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | |
+| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | |
+| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | |
+| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | |
+| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | |
+| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | |
+| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | |
+| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | |
+| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ |
+| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | |
+| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | |
+| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | |
+| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ |
+| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | |
+| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | |
+| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | |
+| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | |
+| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | |
+| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | |
+| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | |
+|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | |
+| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | |
+| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | |
 
 ✅︎ indicates the model is supported on that backend. Empty cells mean not listed as supported on that backend.
 

docs/user_guide/diffusion/attention_backends.md

@@ -283,20 +283,23 @@ blocks — use Ulysses SP (`ring_degree=1`).
 
 ### Which geometries run sparse
 
-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.
+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.
 
-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.
+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.
 
-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.
+"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`.
 
 ## End-to-End Benchmark (BF16, sm_120 RTX Pro 6000 Blackwell)
 

docs/user_guide/diffusion/lora.md

@@ -1,18 +1,14 @@
 # LoRA (Low-Rank Adaptation) Guide
 
-LoRA (Low-Rank Adaptation) enables fine-tuning diffusion models by adding trainable low-rank matrices to existing model weights. vLLM-Omni supports two LoRA backends: **PEFT** for PEFT-style adapters, and **Distill** usually for few-steps inference. **PEFT** backend allows you to customize model behavior without modifying the base model weights. **Distill** backend fuses LoRA weights into the base model at initialization.
+LoRA (Low-Rank Adaptation) enables fine-tuning diffusion models by adding trainable low-rank matrices to existing model weights. vLLM-Omni currently supports PEFT-style LoRA adapters, allowing you to customize model behavior without modifying the base model weights.
 
 ## Overview
 
-LoRA adapters are lightweight, model-specific fine-tuning weights that can be applied to diffusion models in two ways:
-
-- **PEFT backend** (`--lora-backend peft`, default): Loads a PEFT-format adapter folder via `DiffusionLoRAManager`. Adapters are cached (LRU) and activated per request via `LoRARequest`. It uses a unified LoRA handling mechanisms similar to vLLM with LRU cache management.
-- **Distill backend** (`--lora-backend distill`): Calls `pipeline.load_lora_weights` once at initialization to fuse one or more concrete checkpoint files directly into the base weights. Typically used for distilled few-step LoRAs (e.g. Lightning, LightX2V).
+LoRA adapters are lightweight, model-specific fine-tuning weights that can be dynamically loaded and applied to diffusion models. vLLM-Omni uses a unified LoRA handling mechanism similar to vLLM with LRU cache management.
 
 ## LoRA Adapter Format
 
-### PEFT (Parameter-Efficient Fine-Tuning) format (default)
-A typical PEFT-format LoRA adapter directory structure:
+LoRA adapters must be in **PEFT (Parameter-Efficient Fine-Tuning)** format. A typical LoRA adapter directory structure:
 
 ```
 lora_adapter/
@@ -29,20 +25,19 @@ The `adapter_config.json` file contains metadata about the LoRA adapter, includi
 
 ### Offline Inference
 
-#### PEFT backend: pre-loaded LoRA
+#### Pre-loaded LoRA
 
-Load a PEFT-format LoRA adapter at initialization. The adapter is pre-loaded into the cache and can be activated per request:
+Load a LoRA adapter at initialization. This adapter is pre-loaded into the cache and can be activated by requests:
 
 ```python
 from vllm_omni import Omni
 from vllm_omni.lora.request import LoRARequest
 
-lora_path = "/path/to/lora_adapter"
+lora_path="/path/to/lora_adapter"
 
 omni = Omni(
     model="stabilityai/stable-diffusion-3.5-medium",
-    lora_path=lora_path,
-    lora_backend="peft",  # default, can be omitted
+    lora_path=lora_path
 )
 
 lora_request = LoRARequest(
@@ -58,98 +53,6 @@ outputs = omni.generate(
 )
 ```
 
-#### Distill backend: fuse distilled LoRA at init
-
-For distilled few-step LoRAs, pass `lora_backend="distill"` together with one or more concrete `.safetensors` files. The weights are fused into the base model once at init; subsequent `generate()` calls do not need a `LoRARequest`.
-
-##### Supported pipelines
-
-For Qwen-Image and Wan pipelines, the distill backend calls `pipeline.load_lora_weights(...)` during worker initialization.
-
-| Pipeline | Supported distilled LoRA repo | Notes |
-|----------|--------------------------------|-------|
-| `QwenImagePipeline` | `lightx2v/Qwen-Image-2512-Lightning` | Used with Qwen-Image-2512 Lightning-style few-step inference. |
-| `Wan22Pipeline` | `lightx2v/Wan2.1-Distill-Loras`, `lightx2v/Wan2.2-Distill-Loras` | Wan2.1 uses one LoRA file. For dual-transformer Wan2.2 MoE, pass high-noise then low-noise LoRA files. |
-| `Wan22I2VPipeline` | `lightx2v/Wan2.2-Distill-Loras` | For dual-transformer Wan2.2 MoE, pass high-noise then low-noise LoRA files. |
-
-Other diffusion pipelines are not currently listed as supporting distilled LoRA. Use the PEFT backend for request-time adapters, or bake converted weights into a local Diffusers directory before serving.
-
-Single-file example (Qwen-Image-Lightning):
-
-```python
-from vllm_omni import Omni
-
-omni = Omni(
-    model="Qwen/Qwen-Image-2512",
-    lora_path="/path/to/Qwen-Image-2512-Lightning.safetensors",
-    lora_backend="distill",
-)
-
-outputs = omni.generate(prompt="A piece of cheesecake")
-```
-
-Multi-file example (Wan2.2 MoE, high + low noise):
-
-```python
-from vllm_omni import Omni
-
-omni = Omni(
-    model="Wan-AI/Wan2.2-T2V-A14B-Diffusers",
-    lora_path=[
-        "/path/to/wan2.2_high_noise_lora.safetensors",   # -> transformer
-        "/path/to/wan2.2_low_noise_lora.safetensors",    # -> transformer_2
-    ],
-    lora_backend="distill",
-)
-```
-
-The CLI examples under `examples/offline_inference/` accept the same flags, e.g.:
-
-```bash
-python examples/offline_inference/text_to_video/text_to_video.py \
-  --model Wan-AI/Wan2.2-T2V-A14B-Diffusers \
-  --lora-backend distill \
-  --lora-path /path/to/high.safetensors /path/to/low.safetensors \
-  --prompt "A cat playing with yarn"
-```
-
-##### Online serving
-
-Distilled LoRAs can also be fused when an online diffusion server starts. The
-adapter remains active for the lifetime of that server, so requests do not pass
-a per-request `lora` field.
-
-```bash
-vllm serve Qwen/Qwen-Image-2512 \
-  --omni \
-  --port 8091 \
-  --lora-backend distill \
-  --lora-path /path/to/Qwen-Image-2512-Lightning-4steps.safetensors
-```
-
-Then send a normal generation request with the sampling settings expected by
-the distilled checkpoint:
-
-```bash
-curl -s http://localhost:8091/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "messages": [
-      {"role": "user", "content": "A Chinese female college student, around 20 years old, with a very short haircut that conveys a gentle, artistic vibe. Her hair naturally falls to partially cover her cheeks, projecting a tomboyish yet charming demeanor. She has cool-toned fair skin and delicate features, with a slightly shy yet subtly confident expression—her mouth crooked in a playful, youthful smirk. She wears an off-shoulder top, revealing one shoulder, with a well-proportioned figure. The image is framed as a close-up selfie: she dominates the foreground, while the background clearly shows her dormitory—a neatly made bed with white linens on the top bunk, a tidy study desk with organized stationery, and wooden cabinets and drawers. The photo is captured on a smartphone under soft, even ambient lighting, with natural tones, high clarity, and a bright, lively atmosphere full of youthful, everyday energy."}
-    ],
-    "extra_body": {
-      "height": 1024,
-      "width": 1024,
-      "num_inference_steps": 4,
-      "true_cfg_scale": 1.0,
-      "seed": 42
-    }
-  }' | jq -r '.choices[0].message.content[0].image_url.url' | cut -d',' -f2 | base64 -d > qwen_image_distill_lora_output.png
-```
-
-For Wan2.2 MoE serving, pass the high-noise checkpoint first and the low-noise
-checkpoint second to `--lora-path`.
-
 !!! note "Server-side Path Requirement"
     The LoRA adapter path (`local_path`) must be readable on the **server** machine. If your client and server are on different machines, ensure the LoRA adapter is accessible via a shared mount or copied to the server.
 
@@ -238,7 +141,6 @@ Notes:
 
 - This route avoids runtime LoRA loading changes in vLLM-Omni when you choose to bake converted weights into a local Diffusers directory.
 - Output quality and speed depend on the replacement checkpoints and sampling params you choose.
-- If you only need to fuse distilled LoRAs into a Wan2.2 checkpoint at load time (without the full LightX2V convert + assemble pipeline), you can instead pass them directly via `--lora-backend distill --lora-path <high>.safetensors <low>.safetensors`. See the [Distill backend](#distill-backend-fuse-distilled-lora-at-init) section above.
 
 
 ## See Also

docs/user_guide/diffusion/parallelism/sequence_parallel.md

@@ -164,12 +164,10 @@ In `DiffusionParallelConfig`:
 | `ulysses_degree` | int | 1 | Number of GPUs for Ulysses-SP. Uses all-to-all communication. |
 | `ring_degree` | int | 1 | Number of GPUs for Ring-Attention. Uses P2P ring communication. |
 | `ulysses_mode` | str | `"default"` | Ulysses attention mode. Set to `"advanced_uaa"` to handle arbitrary sequence lengths and head counts without padding. |
-| `mask_sp_padding` | bool | `False` | When the sequence length is not divisible by the SP size, tokens are auto-padded with zeros. Set to `True` to mask those padding tokens (strict, but uses the slower varlen attention path); the default `False` leaves them unmasked, keeping the fast path with negligible numerical impact. |
 
 **Notes:**
 - Total sequence parallel size equals to `ulysses_degree × ring_degree`
 - Degrees must evenly divide the sequence length for optimal performance (or use `ulysses_mode="advanced_uaa"` for Ulysses-SP)
-- `mask_sp_padding` is an experimental feature, currently only supported by `Wan2.2`, `Wan2.2 Vace`, `Qwen-Image`, `Flux 2`, and `HunyuanVideo 1.5`
 
 
 ## Best Practices

docs/user_guide/diffusion/startup_and_loading.md

@@ -1,60 +0,0 @@
-# Diffusion Startup and Loading
-
-Large diffusion models can take several minutes to load at startup. vLLM-Omni
-loads safetensors shards in parallel to reduce this initialization time.
-
-Multi-thread weight loading is enabled by default with four threads. No
-configuration is needed for the default behavior.
-
-## Configuration
-
-| Parameter | CLI flag | Default | Description |
-| --- | --- | --- | --- |
-| `enable_multithread_weight_load` | `--disable-multithread-weight-load` | `True` | Pass the flag to disable multi-thread loading |
-| `num_weight_load_threads` | `--num-weight-load-threads` | `4` | Number of parallel weight-loading threads |
-
-!!! tip
-
-    The default balances startup speed and disk I/O contention. Fast NVMe
-    storage may benefit from more threads, while network storage or hard disks
-    may not.
-
-## Online Serving
-
-```bash
-# Default: multi-thread loading with four threads
-vllm serve Qwen/Qwen-Image --omni --port 8091
-
-# Increase the thread count
-vllm serve Wan-AI/Wan2.2-I2V-A14B-Diffusers --omni \
-  --num-weight-load-threads 8
-
-# Disable multi-thread loading
-vllm serve Qwen/Qwen-Image --omni --disable-multithread-weight-load
-```
-
-## Offline Inference
-
-```python
-from vllm_omni import Omni
-
-# Default: multi-thread loading with four threads
-omni = Omni(model="Qwen/Qwen-Image")
-
-# Increase the thread count
-omni = Omni(
-    model="Wan-AI/Wan2.2-I2V-A14B-Diffusers",
-    num_weight_load_threads=8,
-)
-```
-
-## Reference Benchmarks
-
-The following measurements were collected on NVIDIA H800 hardware. Treat them
-as reference results rather than a guarantee for other storage or hardware
-configurations.
-
-| Model | Sequential loading | Multi-thread loading | Speedup |
-| --- | ---: | ---: | ---: |
-| **Qwen/Qwen-Image** (53.7 GiB) | 168 s | 27 s | **6.2x** |
-| **Wan-AI/Wan2.2-I2V-A14B-Diffusers** (64.5 GiB) | 283 s | 56 s | **5.1x** |

docs/user_guide/diffusion_features.md

@@ -49,7 +49,7 @@ Parallelism methods distribute computation across GPUs without quality loss (mat
 
 | Method | Description | Best For |
 |--------|-------------|----------|
-| **[Multi-Thread Weight Loading](diffusion/startup_and_loading.md)** | Loads safetensors shards in parallel using a thread pool | All diffusion models; reduces startup from minutes to seconds |
+| **[Multi-Thread Weight Loading](#multi-thread-weight-loading)** | Loads safetensors shards in parallel using a thread pool | All diffusion models; reduces startup from minutes to seconds |
 
 **Note:** Some acceleration methods can be combined together for optimized performance. See [Feature Compatibility Table](#feature-compatibility) and [Feature Compatibility Tutorial](feature_compatibility.md) for detailed configuration examples.
 
@@ -100,9 +100,7 @@ The following tables show which models support each feature:
 
 - **🔀SP (Ulysses & Ring)**: Includes both Ulysses-SP and Ring-Attention methods
 - ✅ = Fully supported
-- ✅* = Supported with the constraint listed below the table
 - ❌ = Not supported
-- ❓ = Not verified; not recommended
 
 > Notes:
 
@@ -121,7 +119,7 @@ The following tables show which models support each feature:
 | **FLUX.2-dev**           |     ✅     |     ✅      |           ✅           |       ✅        |         ✅         |          ❌          |   ✅    |             ✅             |          ✅           |       ❌        |        ❌         |
 | **GLM-Image**            |     ❌     |     ❌      |           ❌           |       ✅        |         ✅         |          ❌          |   ✅    |             ❌             |          ❌           |       ❌        |        ❌         |
 | **Hidream-I1-Full**        |     ❌     |     ❌      |           ❌           |       ❌        |         ✅         |          ❌          |   ❌    |             ❌             |          ❌           |       ❌        |        ❌         |
-| **HunyuanImage3**        |     ❌     |     ✅      |           ❌           |       ❌        |         ✅         |          ❌          |   ❌    |             ❌             |          ❌           |       ✅        |        ✅*        |
+| **HunyuanImage3**        |     ❌     |     ✅      |           ❌           |       ❌        |         ✅         |          ❌          |   ❌    |             ❌             |          ❌           |       ✅        |        ❌         |
 | **Krea 2**               |     ❌     |     ✅      |           ❌           |       ❌        |         ❌         |          ❌          |   ✅    |             ✅             |      ✅ (decode)      |       ❌        |        ❌         |
 | **LongCat-Image**        |     ✅     |     ✅      |           ✅           |       ✅        |         ✅         |          ❌          |   ❌    |             ✅             |          ❌           |       ❌        |        ❌         |
 | **LongCat-Image-Edit**   |     ✅     |     ✅      |           ✅           |       ✅        |         ✅         |          ❌          |   ❌    |             ✅             |          ❌           |       ❌        |        ❌         |
@@ -147,7 +145,6 @@ The following tables show which models support each feature:
 > 2. `Tongyi-MAI/Z-Image-Turbo` and `SII-GAIR/daVinci-MagiHuman-Base-1080p` are distilled models with minimal NFEs; CFG-Parallel is not necessary.
 > 3. Cosmos3 T2I uses `Cosmos3OmniDiffusersPipeline` with `modalities=["image"]`. Model-level CPU offload swaps the nested UND reasoner and GEN generator pathways; layerwise offload remains available for blockwise GEN/UND offload.
 > 4. Krea 2 currently supports single-GPU inference plus LoRA, Cache-DiT, HSDP, CPU/layerwise offload, and VAE-patch-parallel (decode). TP/SP/CFG-Parallel are not yet wired. The few-step distilled (Turbo) checkpoint uses `is_distilled=true` (fixed timestep shift `mu=1.15`); generate at 2048x2048 by default with `num_inference_steps≈8` and `guidance_scale=0`. The Raw checkpoint uses 1024x1024, `num_inference_steps=28`, and `guidance_scale=4.5`.
-> 5. HunyuanImage3 supports step execution. Multi-request step execution requires `TORCH_SDPA`; see [Diffusion Execution Modes](diffusion/execution_modes.md#step-execution).
 
 ### VideoGen
 
@@ -158,15 +155,11 @@ The following tables show which models support each feature:
 | **Wan2.1-VACE**              |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |      ✅ (decode)      |       ❌        |        ❌         |
 | **LTX-2**                    |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |      ✅ (decode)      |       ❌        |        ❌         |
 | **LTX-2.3**                  |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |      ✅ (decode)      |       ❌        |        ❌         |
-| **Helios**                   |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |          ❌           |       ❌        |        ✅*        |
+| **Helios**                   |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |          ❌           |       ❌        |        ❌         |
 | **HunyuanVideo-1.5 T2V I2V** |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |  ✅ (encode/decode)   |       ✅        |        ❌         |
 | **DreamID-Omni**             |     ❌     |     ❌      |           ❌           |       ✅        |         ❌         |         ❌         |   ✅    |             ✅             |          ❌           |       ❌        |        ❌         |
 | **Cosmos3**                  |     ❌     |     ✅      |           ✅           |       ✅        |         ✅         |         ❌         |   ✅    |             ✅             |  ✅ (encode/decode)   |       ✅        |        ❌         |
-| **LongCat-Video-Avatar-1.5** |     ❌     |     ❌      |           ❌           |       ❌        |         ❌         |         ❌         |   ❌    |             ❌             |          ❌           |       ❌        |        ❌         |
-| **MiniMax-H3**               | ✅ (FL2VA) |     ✅      |           ✅           |       ❌        |       ✅ (DiT/TE)  |         ❌         |   ✅    |             ✅             |       ✅ (tile)       |      ✅ (DiT)      |        ❌         |
-
-> **Step execution note:** Helios supports single-request step execution only;
-> use `max_num_seqs=1`.
+| **MiniMax-H3**               |     ❌     |     ✅      |           ✅           |       ❌        |       ✅ (DiT/TE)  |         ❌         |   ✅    |             ✅             |       ✅ (tile)       |      ✅ (DiT)      |        ❌         |
 
 **Frame Interpolation Support**
 
@@ -196,7 +189,7 @@ The following tables show which models support each feature:
 | **🔀Ring-Attn** | ✅ | ✅ | ✅ | | | | | | | | | | | |
 | **🔀CFG-Parallel** | ✅ | ✅ | ✅ | ✅ | | | | | | | | | | |
 | **🔀Tensor Parallel** | ✅ | ✅ | ✅ | ✅ | ✅ | | | | | | | | | |
-| **🔀HSDP** | ❓ | ❓ | ✅ | ❓ | ✅ | ❌ | | | | | | | | |
+| **🔀HSDP** | ❓ | ❓ | ❓ | ❓ | ❓ | ❌ | | | | | | | | |
 | **🔀Expert Parallel** | ❓ | ❓ | ❓ | ❓ | ❓ | ❓ | ❓ | | | | | | | |
 | **💾CPU Offloading (Layerwise)** | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | | | | | | |
 | **💾CPU Offloading (Module-wise)** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ❓ | ❌ | | | | | |
@@ -207,43 +200,97 @@ The following tables show which models support each feature:
 
 !!! info
 
-    1. HSDP can be combined with Ulysses-SP or CFG-Parallel. Tensor Parallel
-       and HSDP are not compatible; other HSDP combinations in the table
-       remain unverified.
+    1. Tensor Parallel and HSDP are not compatible.
     2. TeaCache and Cache-DiT are not compatible.
     3. CPU Offloading (Layerwise) and CPU Offloading (Module-wise) are not compatible.
-    4. The CPU Offloading (Layerwise) row describes local layerwise offload.
-       Multi-device Distributed Layerwise Offload has a separate topology and
-       compatibility matrix in the [CPU Offloading guide](diffusion/cpu_offload.md#distributed-layerwise-offloading).
-    5. The compatibility matrix uses FP8 as the representative quantization method.
+    4. CPU Offloading (Layerwise) supports single-card for now.
+    5. Using FP8-Quant as an example of qunatization methods.
     6. Step Execution is not compatible with any diffusion cache backend. LoRA is supported, but each scheduled batch must use a single adapter (requests with different `lora_request` or `lora_scale` are kept in separate batches).
 
 
 ## Multi-Thread Weight Loading
 
-The loading guide now lives at [Diffusion Startup and
-Loading](diffusion/startup_and_loading.md). This heading remains so existing
-links to this section continue to work.
+Large diffusion models can take several minutes to load weights at startup (e.g., ~3 min for Qwen-Image, ~5 min for Wan2.2 I2V 14B). Multi-thread weight loading speeds up this process by loading safetensors shards in parallel using a thread pool instead of sequentially.
+
+This optimization is **enabled by default** with 4 threads. No configuration is needed for the default behavior.
+
+### Configuration
+
+| Parameter | CLI Flag | Default | Description |
+|-----------|----------|---------|-------------|
+| `enable_multithread_weight_load` | `--disable-multithread-weight-load` | `True` (enabled) | Pass the flag to disable multi-thread loading |
+| `num_weight_load_threads` | `--num-weight-load-threads` | `4` | Number of threads for parallel weight loading |
+
+!!! tip
+    The default of 4 threads balances speed and disk I/O contention. On fast NVMe storage you may benefit from more threads (e.g., 8). On HDD or network storage, the default of 4 avoids saturating I/O bandwidth.
+
+### Online Serving
+
+```bash
+# Default (multi-thread enabled, 4 threads)
+vllm serve Qwen/Qwen-Image --omni --port 8091
+
+# Custom thread count
+vllm serve Wan-AI/Wan2.2-I2V-A14B-Diffusers --omni --num-weight-load-threads 8
+
+# Disable multi-thread loading
+vllm serve Qwen/Qwen-Image --omni --disable-multithread-weight-load
+```
+
+### Offline Inference
+
+```python
+from vllm_omni import Omni
+
+# Default (multi-thread enabled, 4 threads)
+omni = Omni(model="Qwen/Qwen-Image")
+
+# Custom thread count
+omni = Omni(
+    model="Wan-AI/Wan2.2-I2V-A14B-Diffusers",
+    num_weight_load_threads=8,
+)
+```
+
+### Benchmarks
+
+Measured on NVIDIA H800:
+
+| Model | Before | After | Speedup |
+|-------|--------|-------|---------|
+| **Qwen/Qwen-Image** (53.7 GiB) | 168s | 27s | **6.2x** |
+| **Wan-AI/Wan2.2-I2V-A14B-Diffusers** (64.5 GiB) | 283s | 56s | **5.1x** |
 
 ## Learn More
 
-The Diffusion Acceleration navigation groups the remaining guides as follows:
+**Cache Acceleration:**
 
-| Area | Guide |
-| --- | --- |
-| Compatibility | [Feature Compatibility](feature_compatibility.md) |
-| CPU offloading | [CPU Offloading](diffusion/cpu_offload.md) |
-| Cache acceleration | [TeaCache](diffusion/cache_acceleration/teacache.md), [Cache-DiT](diffusion/cache_acceleration/cache_dit.md) |
-| Parallelism | [Parallelism Overview](diffusion/parallelism/overview.md) |
-| Attention | [Attention Backends](diffusion/attention_backends.md) |
-| Compilation | [Regional Compilation](diffusion/regional_compilation.md) |
-| Video extension | [Frame Interpolation](diffusion/frame_interpolation.md) |
-| Startup | [Startup and Loading](diffusion/startup_and_loading.md) |
-| Adapters | [LoRA](diffusion/lora.md) |
+- **[TeaCache Configuration Guide](diffusion/cache_acceleration/teacache.md)** - Parameter tuning, performance tips, troubleshooting
+- **[Cache-DiT Advanced Guide](diffusion/cache_acceleration/cache_dit.md)** - DBCache, TaylorSeer, SCM techniques and optimization
 
-Related cross-model and runtime features are documented separately:
+**Parallelism Methods:**
 
-- [Quantization](quantization/overview.md) covers diffusion-only models,
-  multi-stage omni/TTS models, and multi-stage diffusion models.
-- [Execution Modes and Streaming](diffusion/execution_modes.md) covers the
-  diffusion runtime, including batching, step execution, and streaming output.
+- **[Parallelism Overview](diffusion/parallelism/overview.md)** - Tensor Parallelism, Sequence Parallelism, CFG Parallelism, Pipeline Parallelism, HSDP, and Expert Parallelism
+
+**Memory Optimization:**
+
+- **[CPU Offload Guide](diffusion/cpu_offload.md)** - Offload model components to CPU, reduce GPU memory usage
+- **[VAE Parallelism Guide](diffusion/parallelism/vae_parallelism.md)** - Distribute VAE decode work across GPUs for high-resolution images and videos
+- **[Quantization](quantization/overview.md)** - Quantization methods for diffusion, multi-stage omni/TTS, and multi-stage diffusion models
+
+**Extensions:**
+
+- **[LoRA Inference Guide](diffusion/lora.md)** - Low-Rank Adaptation for style customization and fine-tuning
+- **[Frame Interpolation Guide](diffusion/frame_interpolation.md)** - Worker-side post-generation video frame interpolation for smoother motion
+
+**Execution Modes:**
+
+- **[Diffusion Execution Modes](diffusion/execution_modes.md)** - Configure request batching, step execution, continuous batching, and streaming output
+
+**Startup Optimization:**
+
+- **[Multi-Thread Weight Loading](#multi-thread-weight-loading)** - Speed up model startup by loading safetensors shards in parallel
+
+**Advanced Topics:**
+
+- **[Feature Compatibility](feature_compatibility.md)** - How to combine multiple features for maximum performance

docs/user_guide/examples/offline_inference/text_to_image.md

@@ -88,9 +88,8 @@ python text_to_image.py \
 | `--vae-use-tiling` | flag | off | Enable VAE tiling for memory optimization |
 | `--cfg-parallel-size` | int | `1` | Set to `2` to enable CFG Parallel |
 | `--enable-cpu-offload` | flag | off | Enable CPU offloading for diffusion models |
-| `--lora-path` | str | — | Path to PEFT LoRA adapter folder or checkpoint file |
+| `--lora-path` | str | — | Path to PEFT LoRA adapter folder |
 | `--lora-scale` | float | `1.0` | Scale factor for LoRA weights |
-| `--lora-backend` | str |`"peft"`| LoRA backend for loading LoRA adapters. Default: peft. Available options: peft, distill |
 
 **NextStep-1.1 specific arguments:**
 

docs/user_guide/examples/offline_inference/text_to_video.md

@@ -125,9 +125,6 @@ python text_to_video.py \
 - `--audio-sample-rate`: fallback audio sample rate when the pipeline returns audio.
 - `--quantization`: quantization method (`fp8` for FP8, `gguf` for GGUF).
 - `--flow-shift`: scheduler flow_shift parameter.
-- `--lora-path`: path to PEFT LoRA adapter folder or checkpoint file.
-- `--lora-scale`: scale factor for LoRA weights.
-- `--lora-backend`: backend for loading LoRA adapters. Default: peft. Available options: peft, distill.
 
 ### Wan2.2-specific
 

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](../../diffusion/attention_backends.md)
+[vLLM-Omni standard of attention backend setting](../../../docs/user_guide/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.

docs/user_guide/quantization/overview.md

@@ -12,20 +12,20 @@ For the internal architecture and backend extension points, see the
 
 | Mode | Guide | Description | Methods |
 |------|-------|-------------|---------|
-| Online quantization | [Online Quantization](online.md) | vLLM-Omni computes quantized weights and scales while loading the model. | FP8 W8A8, Int8 W8A8, BitsAndBytes W4, MXFP8 W8A8, MXFP4 W4A4 |
+| Online quantization | [Online Quantization](online.md) | vLLM-Omni computes quantized weights and scales while loading the model. | FP8 W8A8, Int8 W8A8, MXFP8 W8A8, MXFP4 W4A4 |
 | Runtime attention quantization | [Quantized KV Cache](quantized_kvcache.md) | vLLM-Omni dynamically quantizes eligible diffusion Flash Attention tensors during inference. | FP8 FA |
-| Pre-quantized checkpoints | Method-specific guides | The checkpoint or an offline quantizer provides quantized weights and scales before serving. | ModelOpt, AutoRound, msModelSlim, serialized Int8, offline MXFP8, offline MXFP4 DualScale |
+| Pre-quantized checkpoints | Method-specific guides | The checkpoint or an offline quantizer provides quantized weights and scales before serving. | ModelOpt, GGUF, AutoRound, msModelSlim, serialized Int8, offline MXFP8, offline MXFP4 DualScale |
 
 ## Hardware Support
 
-| Device | FP8 W8A8 | Int8 W8A8 | BitsAndBytes W4 | ModelOpt | MXFP8 W8A8 | MXFP4 W4A4 | AutoRound | msModelSlim |
-|--------|----------|-----------|------------------|----------|------------|------------|-----------|-------------|
-| NVIDIA Blackwell GPU (SM 100+) | ✅ | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ❌ |
-| NVIDIA Ada/Hopper GPU (SM 89+) | ✅ | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ❌ |
-| NVIDIA Ampere GPU (SM 80+) | ✅ | ✅ | ✅ | ⭕ | ⭕ | ⭕ | ✅ | ❌ |
-| AMD ROCm | ⭕ | ⭕ | ❌ | ⭕ | ⭕ | ✅ | ⭕ | ❌ |
-| Intel XPU | ⭕ | ⭕ | ❌ | ⭕ | ⭕ | ⭕ | ✅ | ❌ |
-| Ascend NPU | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ |
+| Device | FP8 W8A8 | Int8 W8A8 | ModelOpt | MXFP8 W8A8 | MXFP4 W4A4 | GGUF | AutoRound | msModelSlim |
+|--------|----------|-----------|----------|------------|------------|------|-----------|-------------|
+| NVIDIA Blackwell GPU (SM 100+) | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ✅ | ❌ |
+| NVIDIA Ada/Hopper GPU (SM 89+) | ✅ | ✅ | ✅ | ⭕ | ⭕ | ✅ | ✅ | ❌ |
+| NVIDIA Ampere GPU (SM 80+) | ✅ | ✅ | ⭕ | ⭕ | ⭕ | ✅ | ✅ | ❌ |
+| AMD ROCm | ⭕ | ⭕ | ⭕ | ⭕ | ✅ | ⭕ | ⭕ | ❌ |
+| Intel XPU | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ | ⭕ | ✅ | ❌ |
+| Ascend NPU | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ |
 
 Legend: `✅` supported, `❌` unsupported, `⭕` not verified in this
 guide. FP8 on Ampere may use a weight-only path where available.
@@ -43,10 +43,10 @@ otherwise.
 |--------|-------|------|----------------|--------|
 | FP8 W8A8 | [FP8](fp8.md) | Online W8A8 or checkpoint FP8 | Qwen-Image; Wan2.2 is not validated | Validated for Qwen-Image family and other DiT models |
 | Int8 W8A8 | [Int8](int8.md) | Online or serialized W8A8 | Qwen-Image; Wan2.2 is not validated | Validated for Qwen-Image and Z-Image |
-| BitsAndBytes W4 | [BitsAndBytes](bitsandbytes.md) | Online W4 weight-only | Z-Image-Turbo; Qwen-Image/Wan2.2 not validated | Validated for Z-Image-Turbo |
 | ModelOpt | [ModelOpt](modelopt.md) | Pre-quantized FP8 checkpoints | Qwen-Image, Z-Image, FLUX.2, HunyuanImage-3.0 | Validated for ModelOpt FP8 diffusion checkpoints |
 | MXFP8 W8A8 | [MXFP8](mxfp8.md) | Online W8A8 or offline pre-quantized | Wan2.2-T2V-A14B, I2V-A14B, TI2V-5B | Ascend NPU only; validated for Wan2.2 |
 | MXFP4 W4A4 | [MXFP4](mxfp4.md) | `mxfp4`: online single-scale only; `mxfp4_dualscale`: online or offline dual-scale (offline recommended) | Wan2.2-T2V-A14B, I2V-A14B | Ascend NPU only; validated for Wan2.2 A14B cascade models; TI2V-5B not supported; offline `mxfp4_dualscale` uses calibrated `mul_scale` for best accuracy |
+| GGUF | [GGUF](gguf.md) | Pre-quantized transformer weights | Qwen-Image | Validated where a model-specific GGUF adapter exists |
 | AutoRound | [AutoRound](autoround.md) | Pre-quantized W4A16 checkpoints | FLUX.1-dev; Qwen-Image/Wan2.2 not validated | Checkpoint-driven |
 | msModelSlim | [msModelSlim](msmodelslim.md) | Pre-quantized Ascend checkpoints | Wan2.2 recipe; HunyuanImage-3.0 inference target | Ascend/NPU path |
 
@@ -61,9 +61,9 @@ in BF16 unless the model guide explicitly adds support.
 |--------|-------|-------|----------------|--------|
 | ModelOpt | [ModelOpt](modelopt.md) | Thinker or language-model checkpoint config | Qwen3-Omni thinker | ModelOpt checkpoint path |
 | Int8 | [Int8](int8.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
-| BitsAndBytes | [BitsAndBytes](bitsandbytes.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
 | MXFP8 | [MXFP8](mxfp8.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
 | MXFP4 | [MXFP4](mxfp4.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
+| GGUF | [GGUF](gguf.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
 | AutoRound | [AutoRound](autoround.md) | Thinker or language-model checkpoint config | Qwen2.5-Omni, Qwen3-Omni | Supported through AutoRound checkpoints |
 | msModelSlim | [msModelSlim](msmodelslim.md) | Not currently validated for omni/TTS stages | Qwen3-Omni, Qwen3-TTS | Not validated |
 
@@ -76,10 +76,10 @@ attached to the intended stage rather than applied globally.
 |--------|-------|-------|----------------|--------|
 | FP8 | [FP8](fp8.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Requires model-specific validation |
 | Int8 | [Int8](int8.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Requires model-specific validation |
-| BitsAndBytes | [BitsAndBytes](bitsandbytes.md) | Stage-specific transformer or DiT module | BAGEL, GLM-Image | Not validated |
 | ModelOpt | [ModelOpt](modelopt.md) | Checkpoint-defined diffusion stage | BAGEL, GLM-Image | Requires model-specific validation |
 | MXFP8 | [MXFP8](mxfp8.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Not validated |
 | MXFP4 | [MXFP4](mxfp4.md) | Stage-specific DiT or transformer module | BAGEL, GLM-Image | Not validated |
+| GGUF | [GGUF](gguf.md) | Stage-specific transformer weights | BAGEL, GLM-Image | No validated adapter listed |
 | AutoRound | [AutoRound](autoround.md) | Checkpoint-defined stage | BAGEL, GLM-Image | No validated checkpoint listed |
 | msModelSlim | [msModelSlim](msmodelslim.md) | Ascend-generated stage weights | GLM-Image | Requires model-specific adaptation |
 
@@ -106,7 +106,7 @@ config = build_quant_config({
 
 | Component | Default quantized? | Notes |
 |-----------|--------------------|-------|
-| Diffusion transformer | Yes | Primary target for FP8, Int8, BitsAndBytes, ModelOpt, MXFP8, MXFP4, AutoRound, and msModelSlim |
+| Diffusion transformer | Yes | Primary target for FP8, Int8, ModelOpt, MXFP8, MXFP4, GGUF, AutoRound, and msModelSlim |
 | Text encoder | No | Keep BF16 unless a method-specific guide documents support |
 | VAE | No | Keep BF16; storage-only paths are method-specific |
 | Scheduler/tokenizer | No | Loaded from the base model repository |
@@ -139,8 +139,8 @@ from vllm_omni.quantization import build_quant_config
 
 build_quant_config("fp8")
 build_quant_config({"method": "fp8", "activation_scheme": "static"})
-build_quant_config("bitsandbytes")
 build_quant_config("auto-round", bits=4, group_size=128)
+build_quant_config({"method": "gguf", "gguf_model": "/path/to/model.gguf"})
 build_quant_config({"transformer": {"method": "fp8"}, "vae": None})
 build_quant_config(None)
 ```

examples/offline_inference/image_to_video/README.md

@@ -33,25 +33,6 @@ This folder provides a unified CLI script for image-to-video generation using vL
 
 Default model: `Wan-AI/Wan2.2-I2V-A14B-Diffusers`.
 
-### LingBot-Video TI2V
-
-LingBot-Video accepts exactly one first-frame image and uses the same dense or
-MoE checkpoint as its T2I and T2V modes:
-
-```bash
-python examples/offline_inference/image_to_video/image_to_video.py \
-  --model robbyant/lingbot-video-dense-1.3b \
-  --model-class-name LingBotVideoPipeline \
-  --image /path/to/input.png \
-  --prompt "the fox looks toward the camera" \
-  --height 192 --width 320 --num-frames 9 --num-inference-steps 2 \
-  --guidance-scale 3.0 --flow-shift 3.0 --fps 24 \
-  --output lingbot_ti2v.mp4
-```
-
-The input image keeps its original geometry until the LingBot pipeline applies
-its model-specific resize and center crop.
-
 ## Prerequisites
 
 Download the example image used in the snippets below:

examples/offline_inference/image_to_video/image_to_video.py

@@ -60,12 +60,8 @@ from vllm_omni.diffusion.data import DiffusionParallelConfig
 from vllm_omni.diffusion.utils.param_utils import apply_declared_extra_args
 from vllm_omni.entrypoints.omni import Omni
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-from vllm_omni.lora.request import LoRARequest
-from vllm_omni.lora.utils import stable_lora_int_id
-from vllm_omni.model_extras import (
-    build_image_to_video_prompt as build_model_image_to_video_prompt,
-)
 from vllm_omni.model_extras import (
+    build_image_to_video_prompt,
     get_extra_body_params,
     get_model_class_name,
 )
@@ -87,22 +83,6 @@ def parse_json_object(value: str, flag_name: str = "argument") -> dict[str, Any]
 parse_profiler_config = functools.partial(parse_json_object, flag_name="--profiler-config")
 
 
-def build_image_to_video_prompt(
-    prompt: str,
-    negative_prompt: str | None,
-    media_inputs: dict[str, Any],
-) -> dict[str, Any]:
-    """Build the canonical request envelope for the shared I2V example."""
-    result: dict[str, Any] = {
-        "prompt": prompt,
-        "modalities": ["video"],
-        "multi_modal_data": media_inputs,
-    }
-    if negative_prompt is not None:
-        result["negative_prompt"] = negative_prompt
-    return result
-
-
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(
         description=(
@@ -314,30 +294,6 @@ def parse_args() -> argparse.Namespace:
         default=None,
         help='JSON profiler config for torch/cuda profiling, e.g. \'{"profiler":"torch","torch_profiler_dir":"./perf"}\'.',
     )
-    parser.add_argument(
-        "--lora-path",
-        type=str,
-        nargs="+",
-        default=None,
-        help="Path to a LoRA adapter folder (PEFT format) or concrete LoRA checkpoint files. "
-        "For Wan2.2 MoE models, pass the high-noise checkpoint first and the low-noise checkpoint second.",
-    )
-    parser.add_argument(
-        "--lora-scale",
-        type=float,
-        default=1.0,
-        help="Scale factor for PEFT LoRA weights (default: 1.0).",
-    )
-    parser.add_argument(
-        "--lora-backend",
-        type=str,
-        default="peft",
-        choices=["peft", "distill"],
-        help=(
-            "LoRA backend. 'peft' loads a PEFT-format adapter for request-time activation; "
-            "'distill' fuses one or more concrete LoRA checkpoint files at initialization."
-        ),
-    )
     parser.add_argument(
         "--extra-body",
         type=functools.partial(parse_json_object, flag_name="--extra-body"),
@@ -531,12 +487,6 @@ def main():
         omni_kwargs["flow_shift"] = flow_shift
     if args.quantization is not None:
         omni_kwargs["quantization"] = args.quantization
-    if args.lora_path is not None:
-        lora_path = args.lora_path
-        if len(lora_path) == 1:
-            lora_path = lora_path[0]
-        omni_kwargs["lora_path"] = lora_path
-        omni_kwargs["lora_backend"] = args.lora_backend
     # Cosmos3 loads its (gated) guardrail models at build time, so the guardrails
     # gate is an engine-level config (offline analog of the server's --no-guardrails).
     if args.extra_body and "guardrails" in args.extra_body:
@@ -567,39 +517,19 @@ def main():
     print(f"  Video size: {width}x{height}")
     print(f"{'=' * 60}\n")
 
-    lora_request = None
-    if args.lora_path and args.lora_backend == "peft":
-        if len(args.lora_path) != 1:
-            raise ValueError("Only one LoRA path is expected for PEFT backend.")
-
-        lora_path = args.lora_path[0]
-        lora_request = LoRARequest(
-            lora_name=Path(lora_path).stem,
-            lora_int_id=stable_lora_int_id(lora_path),
-            lora_path=lora_path,
-        )
-
     negative_prompt = args.negative_prompt
     if negative_prompt is None and not is_ltx2:
         # Preserve the historical empty-prompt behavior for non-LTX examples.
         negative_prompt = ""
     prompt_dict = build_image_to_video_prompt(
+        model_class_name=model_class_name,
         prompt=args.prompt,
         negative_prompt=negative_prompt,
         media_inputs=media_inputs,
-    )
-    prompt_dict = build_model_image_to_video_prompt(
-        model_class_name=model_class_name,
-        prompt=prompt_dict,
         height=height,
         width=width,
         num_frames=num_frames,
     )
-    sampling_extra_args = {"sample_solver": args.sample_solver}
-    if lora_request is not None:
-        sampling_extra_args["lora_request"] = lora_request
-        sampling_extra_args["lora_scale"] = args.lora_scale
-
     sampling_params = OmniDiffusionSamplingParams(
         height=height,
         width=width,
@@ -610,7 +540,7 @@ def main():
         num_inference_steps=num_inference_steps,
         num_frames=num_frames,
         frame_rate=frame_rate,
-        extra_args=sampling_extra_args,
+        extra_args={"sample_solver": args.sample_solver},
     )
     if flow_shift is not None:
         sampling_params.extra_args["flow_shift"] = flow_shift

examples/offline_inference/longcat_video/end2end.py

@@ -1,319 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import argparse
-import json
-import re
-import subprocess
-import tempfile
-import wave
-from functools import lru_cache
-from pathlib import Path
-from typing import Any
-
-import imageio
-import numpy as np
-import torch
-
-from vllm_omni.diffusion.data import DiffusionParallelConfig
-from vllm_omni.diffusion.models.longcat_video.pipeline_longcat_video_avatar import (
-    prepare_longcat_video_avatar_model_for_omni,
-)
-from vllm_omni.entrypoints.omni import Omni
-from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-from vllm_omni.outputs import OmniRequestOutput
-from vllm_omni.platforms import current_omni_platform
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description="Generate LongCat-Video-Avatar A2V/AI2V video.")
-    parser.add_argument("--model", default="meituan-longcat/LongCat-Video-Avatar-1.5")
-    parser.add_argument("--base-model-dir", default=None, help="Optional local LongCat-Video base model directory.")
-    parser.add_argument("--stage", choices=["at2v", "ai2v"], default="at2v")
-    parser.add_argument("--prompt", default="A person speaks calmly while facing the camera.")
-    parser.add_argument("--negative-prompt", default="low quality, blurry, watermark, text")
-    parser.add_argument("--audio", default=None, help="Input speech audio path.")
-    parser.add_argument("--image", default=None, help="Input reference image path for AI2V.")
-    parser.add_argument("--input-json", default=None, help="Official LongCat Avatar JSON case for AI2V.")
-    parser.add_argument("--output", default="longcat_avatar_output.mp4")
-    parser.add_argument("--resolution", choices=["480p", "720p"], default="480p")
-    parser.add_argument("--num-frames", type=int, default=93)
-    parser.add_argument("--num-segments", default="1", help="Number of AVC segments, or 'auto' to cover full audio.")
-    parser.add_argument("--num-cond-frames", type=int, default=13)
-    parser.add_argument("--ref-img-index", type=int, default=10)
-    parser.add_argument("--mask-frame-range", type=int, default=3)
-    parser.add_argument("--fps", type=int, default=25)
-    parser.add_argument("--num-inference-steps", type=int, default=8)
-    parser.add_argument("--seed", type=int, default=42)
-    parser.add_argument("--use-distill", action=argparse.BooleanOptionalAction, default=True)
-    parser.add_argument("--use-int8", action=argparse.BooleanOptionalAction, default=True)
-    parser.add_argument(
-        "--build-components-on-gpu",
-        action="store_true",
-        default=False,
-        help="Build large Avatar components directly on GPU for faster startup. Requires more peak VRAM.",
-    )
-    parser.add_argument("--use-kv-cache", action=argparse.BooleanOptionalAction, default=True)
-    parser.add_argument("--offload-kv-cache", action=argparse.BooleanOptionalAction, default=False)
-    parser.add_argument("--enforce-eager", action="store_true")
-    return parser.parse_args()
-
-
-def _extract_frames(output: Any):
-    if isinstance(output, list):
-        output = output[0] if output else None
-    if isinstance(output, OmniRequestOutput):
-        if not output.images:
-            raise ValueError("No video frames found in OmniRequestOutput.")
-        frames = output.images[0] if len(output.images) == 1 else output.images
-        if isinstance(frames, tuple) and len(frames) == 2:
-            frames = frames[0]
-        if isinstance(frames, dict):
-            frames = frames.get("frames") or frames.get("video")
-    else:
-        frames = output
-    if frames is None:
-        raise ValueError("No video frames found in output.")
-    return frames
-
-
-def _frames_to_uint8(frames):
-    frames_np = np.asarray([np.asarray(frame) for frame in frames])
-    if frames_np.ndim == 5:
-        frames_np = frames_np[0]
-    if np.issubdtype(frames_np.dtype, np.floating):
-        frames_np = (np.clip(frames_np, 0.0, 1.0) * 255).round()
-    return np.clip(frames_np, 0, 255).astype(np.uint8)
-
-
-@lru_cache(maxsize=1)
-def _ffmpeg_exe() -> str:
-    try:
-        import imageio_ffmpeg
-
-        return imageio_ffmpeg.get_ffmpeg_exe()
-    except Exception as exc:
-        raise RuntimeError("LongCat Avatar example requires the Python imageio[ffmpeg] dependency.") from exc
-
-
-def _wav_duration(path: Path) -> float:
-    with wave.open(str(path), "rb") as audio:
-        return audio.getnframes() / float(audio.getframerate())
-
-
-def _save_video_with_audio(frames, output_path: Path, audio_path: str, fps: int) -> None:
-    frames_np = _frames_to_uint8(frames)
-    output_path.parent.mkdir(parents=True, exist_ok=True)
-    with tempfile.TemporaryDirectory(prefix="longcat_avatar_export_") as tmp:
-        tmp_dir = Path(tmp)
-        temp_video = tmp_dir / "video.mp4"
-        crop_audio = tmp_dir / "audio.wav"
-        crop_video = tmp_dir / "video_cropped.mp4"
-        writer = imageio.get_writer(str(temp_video), fps=fps, quality=5)
-        try:
-            for frame in frames_np:
-                writer.append_data(frame)
-        finally:
-            writer.close()
-
-        duration = len(frames_np) / fps
-        ffmpeg = _ffmpeg_exe()
-        subprocess.run([ffmpeg, "-y", "-i", audio_path, "-t", f"{duration}", str(crop_audio)], check=True)
-        audio_duration = _wav_duration(crop_audio)
-        subprocess.run(
-            [
-                ffmpeg,
-                "-y",
-                "-i",
-                str(temp_video),
-                "-t",
-                f"{audio_duration}",
-                "-c:v",
-                "copy",
-                str(crop_video),
-            ],
-            check=True,
-        )
-        subprocess.run(
-            [
-                ffmpeg,
-                "-y",
-                "-i",
-                str(crop_video),
-                "-i",
-                str(crop_audio),
-                "-c:v",
-                "libx264",
-                "-c:a",
-                "aac",
-                "-shortest",
-                str(output_path),
-            ],
-            check=True,
-        )
-
-
-def _infer_asset_root_from_input_json(input_json: Path) -> Path:
-    resolved = input_json.resolve()
-    parts = resolved.parts
-    if "assets" not in parts:
-        return resolved.parent
-    asset_idx = parts.index("assets")
-    return Path(*parts[:asset_idx])
-
-
-def _resolve_case_path(path: str, asset_root: Path) -> str:
-    raw_path = Path(path)
-    if raw_path.is_absolute():
-        return str(raw_path)
-    candidate = asset_root / raw_path
-    return str(candidate if candidate.exists() else raw_path)
-
-
-def _speaker_sort_key(name: str) -> tuple[int, str]:
-    match = re.search(r"(\d+)$", str(name))
-    return (int(match.group(1)) if match else 10_000, str(name))
-
-
-def _load_input_case(input_json: str) -> tuple[dict[str, Any], Path]:
-    input_json_path = Path(input_json)
-    with input_json_path.open("r", encoding="utf-8") as f:
-        case = json.load(f)
-    return case, _infer_asset_root_from_input_json(input_json_path)
-
-
-def _create_merged_audio_for_case(
-    audio_paths: dict[str, str],
-    audio_type: str,
-    output_path: Path,
-) -> str:
-    sorted_paths = [path for _, path in sorted(audio_paths.items(), key=lambda item: _speaker_sort_key(str(item[0])))]
-    if len(sorted_paths) == 1:
-        return sorted_paths[0]
-    inputs = [arg for path in sorted_paths for arg in ("-i", path)]
-    audio_type = audio_type.lower()
-    if audio_type == "para":
-        filter_complex = f"amix=inputs={len(sorted_paths)}:duration=longest:normalize=0"
-    elif audio_type == "add":
-        filter_complex = "".join(f"[{idx}:a]" for idx in range(len(sorted_paths)))
-        filter_complex += f"concat=n={len(sorted_paths)}:v=0:a=1"
-    else:
-        raise NotImplementedError(f"Unsupported LongCat Avatar audio_type {audio_type!r}.")
-    subprocess.run([_ffmpeg_exe(), "-y", *inputs, "-filter_complex", filter_complex, str(output_path)], check=True)
-    return str(output_path)
-
-
-def main():
-    args = parse_args()
-    input_case = None
-    input_asset_root = None
-    audio_for_mux = args.audio
-    if args.input_json:
-        input_case, input_asset_root = _load_input_case(args.input_json)
-        args.stage = "ai2v"
-        args.prompt = input_case.get("prompt") or args.prompt
-        args.image = _resolve_case_path(input_case["cond_image"], input_asset_root)
-        args.audio = None
-    if not args.input_json and not args.audio:
-        raise ValueError("--audio is required unless --input-json is provided.")
-    if args.stage == "ai2v" and not args.image:
-        raise ValueError("--image is required when --stage=ai2v.")
-    model_for_omni = prepare_longcat_video_avatar_model_for_omni(args.model, args.use_int8)
-
-    additional_config = {
-        "model_type": "avatar-v1.5",
-        "resolution": args.resolution,
-        "use_distill": args.use_distill,
-        "use_int8": args.use_int8,
-        "build_components_on_gpu": args.build_components_on_gpu,
-    }
-    if args.base_model_dir:
-        additional_config["base_model_dir"] = args.base_model_dir
-
-    omni = Omni(
-        model=model_for_omni,
-        model_class_name="LongCatVideoAvatarPipeline",
-        dtype="bfloat16",
-        enforce_eager=args.enforce_eager,
-        additional_config=additional_config,
-        parallel_config=DiffusionParallelConfig(
-            ulysses_degree=1,
-            ring_degree=1,
-            cfg_parallel_size=1,
-            tensor_parallel_size=1,
-            vae_patch_parallel_size=1,
-            pipeline_parallel_size=1,
-        ),
-    )
-
-    audio_input: str | dict[str, str] | None = args.audio
-    additional_information = {"stage": args.stage, "resolution": args.resolution}
-    if input_case is not None and input_asset_root is not None:
-        audio_input = {
-            speaker: _resolve_case_path(path, input_asset_root)
-            for speaker, path in sorted(
-                input_case["cond_audio"].items(),
-                key=lambda item: _speaker_sort_key(str(item[0])),
-            )
-        }
-        additional_information.update(
-            {
-                "input_json": args.input_json,
-                "audio_type": input_case.get("audio_type", "para"),
-                "bbox": input_case.get("bbox", {}),
-            }
-        )
-
-    prompt = {
-        "prompt": args.prompt,
-        "negative_prompt": args.negative_prompt,
-        "multi_modal_data": {"audio": audio_input},
-        "additional_information": additional_information,
-    }
-    if args.stage == "ai2v":
-        prompt["multi_modal_data"]["image"] = args.image
-
-    try:
-        output = omni.generate(
-            prompt,
-            OmniDiffusionSamplingParams(
-                generator=torch.Generator(device=current_omni_platform.device_type).manual_seed(args.seed),
-                seed=args.seed,
-                guidance_scale=1.0 if args.use_distill else 4.0,
-                guidance_scale_2=1.0 if args.use_distill else 4.0,
-                num_inference_steps=args.num_inference_steps,
-                num_frames=args.num_frames,
-                fps=args.fps,
-                extra_args={
-                    "stage": args.stage,
-                    "resolution": args.resolution,
-                    "save_fps": args.fps,
-                    "use_distill": args.use_distill,
-                    "use_int8": args.use_int8,
-                    "input_json": args.input_json,
-                    "num_segments": args.num_segments,
-                    "num_cond_frames": args.num_cond_frames,
-                    "ref_img_index": args.ref_img_index,
-                    "mask_frame_range": args.mask_frame_range,
-                    "use_kv_cache": args.use_kv_cache,
-                    "offload_kv_cache": args.offload_kv_cache,
-                },
-            ),
-            use_tqdm=True,
-        )
-    finally:
-        omni.close()
-
-    with tempfile.TemporaryDirectory(prefix="longcat_avatar_audio_mux_") as tmp:
-        if input_case is not None and isinstance(audio_input, dict):
-            audio_for_mux = _create_merged_audio_for_case(
-                audio_input,
-                input_case.get("audio_type", "para"),
-                Path(tmp) / "merged_audio.wav",
-            )
-        _save_video_with_audio(_extract_frames(output), Path(args.output), audio_for_mux, args.fps)
-    print(f"Saved video to {args.output}")
-
-
-if __name__ == "__main__":
-    main()

examples/offline_inference/text_to_image/README.md

@@ -43,24 +43,6 @@ This folder provides several entrypoints for experimenting with text-to-image di
 
 Default model: `Qwen/Qwen-Image`
 
-### LingBot-Video
-
-LingBot-Video uses the same checkpoint for image and video generation. Run the
-shared T2I entry point with:
-
-```bash
-python examples/offline_inference/text_to_image/text_to_image.py \
-  --model robbyant/lingbot-video-dense-1.3b \
-  --prompt "a red fox standing in fresh snow" \
-  --height 192 --width 320 --num-inference-steps 2 \
-  --guidance-scale 3.0 --extra-body '{"flow_shift":3.0}' \
-  --output lingbot_t2i.png
-```
-
-The shared T2I entry point selects the `image` output modality. The LingBot
-pipeline validates that T2I requests produce one frame and do not include an
-input image.
-
 ## Quick Start
 
 ### Python API
@@ -110,9 +92,8 @@ python text_to_image.py \
 | `--ring-degree` | int | `1` | Ring sequence parallel degree for hybrid Ulysses + Ring inference |
 | `--ulysses-mode` | str | `"strict"` | Ulysses SP mode: `"strict"` or `"advanced_uaa"` |
 | `--enable-cpu-offload` | flag | off | Enable CPU offloading for diffusion models |
-| `--lora-path` | str | — | Path to PEFT LoRA adapter folder or checkpoint file |
+| `--lora-path` | str | — | Path to PEFT LoRA adapter folder |
 | `--lora-scale` | float | `1.0` | Scale factor for LoRA weights |
-| `--lora-backend` | str |`"peft"`| LoRA backend for loading LoRA adapters. Default: peft. Available options: peft, distill |
 | `--use-system-prompt` | str | `None` | System prompt preset: `en_unified`, `en_vanilla`, `en_recaption`, `en_think_recaption`, `dynamic`, `None`, or custom text. Recommended: `en_unified`. Only for HunyuanImage-3.0.|
 | `--system-prompt` | str | `None` | Custom system prompt text. Only used when `--use-system-prompt` is set to `custom`. Only for HunyuanImage-3.0.|
 | `--auxiliary-text-encoder` | str | `None` | Supplementary auxiliary text encoder parameters model name or path (especially for Hidream-l1-full). |

examples/offline_inference/text_to_image/text_to_image.py

@@ -8,9 +8,7 @@ import time
 from pathlib import Path
 from typing import Any
 
-import numpy as np
 import torch
-from diffusers.utils import numpy_to_pil
 
 from vllm_omni.diffusion.data import logger
 from vllm_omni.diffusion.utils.image_output import extract_images_from_outputs
@@ -21,9 +19,7 @@ from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 from vllm_omni.lora.request import LoRARequest
 from vllm_omni.lora.utils import stable_lora_int_id
 from vllm_omni.model_extras import (
-    build_text_to_image_prompt as build_model_text_to_image_prompt,
-)
-from vllm_omni.model_extras import (
+    build_text_to_image_prompt,
     get_extra_body_params,
     get_model_class_name,
     should_init_extra_args_for_non_diffusion_stages,
@@ -58,28 +54,6 @@ def parse_json_object(value: str, flag_name: str = "argument") -> dict[str, Any]
 parse_profiler_config = functools.partial(parse_json_object, flag_name="--profiler-config")
 
 
-def build_text_to_image_prompt(prompt: str, negative_prompt: str | None) -> dict[str, Any]:
-    """Build the canonical request envelope for the shared T2I example."""
-    result: dict[str, Any] = {
-        "prompt": prompt,
-        "modalities": ["image"],
-    }
-    if negative_prompt is not None:
-        result["negative_prompt"] = negative_prompt
-    return result
-
-
-def _normalize_images_for_save(images: list[Any]) -> list[Any]:
-    """Convert NumPy diffusion outputs to PIL images before saving."""
-    normalized = []
-    for image in images:
-        if isinstance(image, np.ndarray):
-            normalized.extend(numpy_to_pil(image))
-        else:
-            normalized.append(image)
-    return normalized
-
-
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Generate an image with supported diffusion models.")
     parser.add_argument(
@@ -273,7 +247,6 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--lora-path",
         type=str,
-        nargs="+",
         default=None,
         help="Path to LoRA adapter folder (PEFT format). Loaded at initialization and used for generation.",
     )
@@ -283,15 +256,6 @@ def parse_args() -> argparse.Namespace:
         default=1.0,
         help="Scale factor for LoRA weights (default: 1.0).",
     )
-    parser.add_argument(
-        "--lora-backend",
-        type=str,
-        default="peft",
-        choices=["peft", "distill"],
-        help="LoRA backend for loading LoRA adapters. Default: peft"
-        "'peft' loads a PEFT-format adapter folder, used e.g. for RL"
-        "'distill' fuses one or more concrete LoRA checkpoint files, used e.g. for distilled few-step LoRAs",
-    )
     parser.add_argument(
         "--vae-patch-parallel-size",
         type=int,
@@ -427,12 +391,8 @@ def main():
     # Prepare LoRA kwargs for Omni initialization
     lora_args: dict[str, Any] = {}
     if args.lora_path:
-        lora_path = args.lora_path
-        if len(lora_path) == 1:
-            lora_path = lora_path[0]
-        lora_args["lora_path"] = lora_path
-        lora_args["lora_backend"] = args.lora_backend
-        print(f"Using LoRA from: {lora_path} with backend: {args.lora_backend}")
+        lora_args["lora_path"] = args.lora_path
+        print(f"Using LoRA from: {args.lora_path}")
 
     # Build quantization kwargs: use quantization_config dict when
     # ignored_layers is specified so the list flows through OmniDiffusionConfig
@@ -521,27 +481,20 @@ def main():
 
     # Build LoRA request when --lora-path is set
     lora_request = None
-    if args.lora_path and args.lora_backend == "peft":
-        if len(args.lora_path) != 1:
-            raise ValueError("Only one LoRA path is expected for PEFT backend.")
-
-        lora_path = args.lora_path[0]
-        lora_request_id = stable_lora_int_id(lora_path)
+    if args.lora_path:
+        lora_request_id = stable_lora_int_id(args.lora_path)
         lora_request = LoRARequest(
-            lora_name=Path(lora_path).stem,
+            lora_name=Path(args.lora_path).stem,
             lora_int_id=lora_request_id,
-            lora_path=lora_path,
+            lora_path=args.lora_path,
         )
 
     generation_start = time.perf_counter()
 
     prompt_dict = build_text_to_image_prompt(
+        model_class_name=model_class_name,
         prompt=args.prompt,
         negative_prompt=args.negative_prompt,
-    )
-    prompt_dict = build_model_text_to_image_prompt(
-        model_class_name=model_class_name,
-        prompt=prompt_dict,
         height=args.height,
         width=args.width,
     )
@@ -666,7 +619,6 @@ def main():
 
     if not images:
         raise ValueError("No images found in request_output")
-    images = _normalize_images_for_save(images)
 
     output_path = Path(args.output)
     output_path.parent.mkdir(parents=True, exist_ok=True)

examples/offline_inference/text_to_speech/README.md

@@ -24,7 +24,6 @@ list of supported architectures across all modalities, see
 | Qwen3-TTS | `Qwen/Qwen3-TTS-12Hz-1.7B-{CustomVoice,VoiceDesign,Base}` | 2 (talker + code2wav) | ✓ (Base) | ✓ | 3 task variants | 24 kHz |
 | VoxCPM2 | `openbmb/VoxCPM2` | single (native AR) | ✓ | ✓ (online) | continuation | 48 kHz |
 | IndexTTS-2 | `IndexTeam/IndexTTS-2` | 2 (AR talker + S2Mel DiT + BigVGAN) | ✓ (required) | — | emotion control (`--emo-audio`, `--emo-text`, `--emo-vector`) | 22.05 kHz |
-| IndexTTS-2.5 | native `checkpoints/` bundle | 2 (AR talker + EnhancedCodec + S2Mel DiT + BigVGAN) | ✓ (required) | — | multilingual (`--lang`) + emotion control | 22.05 kHz |
 | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | varies | ✓ | ✓ | voice presets | 24 kHz |
 
 ## Common Quick Start
@@ -438,14 +437,11 @@ Streaming is exposed through the online OpenAI Speech API (`stream=true`). See [
 
 ---
 
-## IndexTTS-2 and IndexTTS-2.5
+## IndexTTS-2
 
-Both versions use a 2-stage TTS pipeline and produce 22.05 kHz mono audio. Stage 0 is a GPT AR talker. IndexTTS-2 Stage 1 uses RepCodec semantic embeddings, GPT latent, S2Mel CFM/DiT, and BigVGAN. IndexTTS-2.5 replaces RepCodec with EnhancedCodec and uses the official code-only path (`use_gpt_latent=false`). Every request requires reference audio for zero-shot voice cloning.
+2-stage TTS pipeline (GPT AR talker + S2Mel CFM DiT + BigVGAN vocoder) at 22.05 kHz. Every request requires reference audio for zero-shot voice cloning. Supports emotion conditioning via audio, text, or 8-dim vector.
 
 ### Quick start
-
-IndexTTS-2:
-
 ```bash
 python examples/offline_inference/text_to_speech/indextts2/end2end.py \
     --model IndexTeam/IndexTTS-2 \
@@ -453,24 +449,6 @@ python examples/offline_inference/text_to_speech/indextts2/end2end.py \
     --ref-audio /path/to/reference.wav
 ```
 
-IndexTTS-2 uses its existing frontend and does not require the IndexTTS-2.5 text dependencies. Before running IndexTTS-2.5, install its optional frontend dependencies:
-
-```bash
-pip install 'vllm-omni[indextts2]'
-```
-
-IndexTTS-2.5 with a native repository/lab bundle whose model root contains `checkpoints/`:
-
-```bash
-python examples/offline_inference/text_to_speech/indextts2/end2end.py \
-    --model /path/to/indextts-2.5 \
-    --model-version 2.5 \
-    --lang ja \
-    --text "こんにちは、音声合成のテストです。" \
-    --ref-audio /path/to/reference.wav
-
-```
-
 ### Emotion control
 ```bash
 # Emotion from reference audio
@@ -496,13 +474,10 @@ python examples/offline_inference/text_to_speech/indextts2/end2end.py \
 ```
 
 ### Notes
-- `--ref-audio` is **required** — neither version provides text-only synthesis.
-- IndexTTS-2.5 Stage 0 (AR Talker) generates mel codes from text + reference audio using plain vLLM sampling. It does not reproduce the official default `num_beams=3` beam search. For parity comparisons, run upstream with `num_beams=1`; output quality can differ from the official beam-search result.
-- IndexTTS-2.5 accepts language codes such as `zh`, `en`, `zhen` (mixed Chinese/English), `ja`, and `yue`. `Mandarin` is a vLLM-Omni convenience alias for `zh`. Japanese (`ja`) uses `fugashi` tokenization and produces audio, but it does not automatically expand numbers, dates, or percentages; write those inputs as readable Japanese text before calling the model. Use `--no-text-normalization` only when the input is already normalized.
-- A seed controls Stage 0 AR sampling and per-request CFM noise. Different concurrent batch compositions do not guarantee a bit-identical waveform.
-- Stage 1 (semantic codec + S2Mel + BigVGAN): CFM/DiT converts the complete semantic-code sequence to waveform.
-- Deploy configs: `vllm_omni/deploy/indextts2.yaml` and `indextts2_5.yaml`.
-- `async_chunk=false` is intentional for IndexTTS-2.5 correctness: S2Mel consumes the completed semantic sequence.
+- `--ref-audio` is **required** — IndexTTS-2 does not support text-only synthesis.
+- Stage 0 (AR Talker): GPT-2 generates mel codes from text + reference audio.
+- Stage 1 (S2Mel + BigVGAN): CFM DiT converts mel codes to waveform at 22.05 kHz.
+- Deploy config: `vllm_omni/deploy/indextts2.yaml`. Stage 1 runs with `enforce_eager: true` (DiT has dynamic shapes).
 
 ---
 

examples/offline_inference/text_to_speech/indextts2/end2end.py

@@ -1,16 +1,13 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Offline inference example for IndexTTS 2.0 and 2.5 via vLLM-Omni.
+"""Offline inference example for IndexTTS2 via vLLM-Omni.
 
-Two-stage pipeline: GPT AR (Stage 0) → semantic codec + S2Mel + BigVGAN
-(Stage 1).
+Two-stage pipeline: GPT AR (Stage 0) → S2Mel + BigVGAN (Stage 1).
 Output is 22050 Hz mono WAV.
 
 Usage:
   python end2end.py \
-    --model /path/to/indextts-2.5 \
-    --model-version 2.5 \
-    --lang zh \
+    --model /path/to/IndexTeam/IndexTTS-2 \
     --text "你好，这是一个语音合成测试。" \
     --ref-audio /path/to/ref.wav
 
@@ -50,10 +47,6 @@ def build_request(
     emo_alpha: float | None = None,
     use_emo_text: bool = False,
     use_random: bool = False,
-    model_type: str = "indextts2",
-    lang: str = "zh",
-    text_normalization: bool = True,
-    tokenizer_file: str | None = None,
 ) -> dict:
     additional: dict = {"text": [text]}
     if ref_audio_path:
@@ -70,44 +63,12 @@ def build_request(
         additional["use_emo_text"] = [True]
     if use_random:
         additional["use_random"] = [True]
-    if model_type == "indextts2_5":
-        additional["lang"] = [lang]
-        additional["text_normalization"] = [text_normalization]
-    prompt_kwargs = {
-        "model_type": model_type,
-        "lang": lang,
-        "text_normalization": text_normalization,
-    }
-    if tokenizer_file is not None:
-        prompt_kwargs["tokenizer_file"] = tokenizer_file
     return {
-        "prompt_token_ids": build_indextts2_prefill_prompt_ids(
-            model,
-            text,
-            **prompt_kwargs,
-        ),
+        "prompt_token_ids": build_indextts2_prefill_prompt_ids(model, text),
         "additional_information": additional,
     }
 
 
-def _get_stage0_tokenizer_file(omni: Omni) -> str | None:
-    """Read the effective tokenizer override from the resolved Stage 0 config."""
-    stage_configs = omni.stage_configs
-    if not stage_configs:
-        return None
-    engine_args = getattr(stage_configs[0], "engine_args", None)
-    if engine_args is None:
-        return None
-    hf_overrides = getattr(engine_args, "hf_overrides", None)
-    if hf_overrides is None and isinstance(engine_args, dict):
-        hf_overrides = engine_args.get("hf_overrides")
-    if hf_overrides is None:
-        return None
-    if hasattr(hf_overrides, "get"):
-        return hf_overrides.get("tokenizer_file")
-    return getattr(hf_overrides, "tokenizer_file", None)
-
-
 def save_audio(waveform: torch.Tensor, path: str, sample_rate: int = 22050) -> None:
     audio_np = waveform.float().numpy()
     sf.write(path, audio_np, sample_rate)
@@ -134,14 +95,9 @@ def extract_audio(mm: dict) -> tuple[torch.Tensor | None, int]:
 
 
 def main(args) -> None:
-    model_type = "indextts2_5" if args.model_version == "2.5" else "indextts2"
-    deploy_config = args.deploy_config
-    if deploy_config is None and args.model_version == "2.5":
-        repo_root = Path(__file__).resolve().parents[4]
-        deploy_config = str(repo_root / "vllm_omni" / "deploy" / "indextts2_5.yaml")
     omni = Omni(
         model=args.model,
-        deploy_config=deploy_config,
+        deploy_config=args.deploy_config,
         stage_init_timeout=args.stage_init_timeout,
     )
 
@@ -170,7 +126,7 @@ def main(args) -> None:
     print(f"Synthesizing: {args.text!r}")
     if args.ref_audio:
         print(f"  ref_audio: {args.ref_audio}")
-    request_kwargs = dict(
+    inputs = build_request(
         model=args.model,
         text=args.text,
         ref_audio_path=args.ref_audio,
@@ -180,17 +136,7 @@ def main(args) -> None:
         emo_alpha=args.emo_alpha,
         use_emo_text=args.use_emo_text,
         use_random=args.use_random,
-        model_type=model_type,
-        lang=args.lang,
-        text_normalization=args.text_normalization,
     )
-    if model_type == "indextts2_5":
-        tokenizer_file = _get_stage0_tokenizer_file(omni)
-        if tokenizer_file is not None:
-            request_kwargs["tokenizer_file"] = tokenizer_file
-    inputs = build_request(**request_kwargs)
-    if model_type == "indextts2_5":
-        inputs["additional_information"]["duration_factor"] = [1.0 / getattr(args, "speed", 1.0)]
 
     for i, omni_out in enumerate(omni.generate(inputs, sampling_params_list=sampling_params)):
         mm = omni_out.multimodal_output
@@ -208,37 +154,8 @@ def main(args) -> None:
 
 
 def parse_args():
-    parser = FlexibleArgumentParser(description="IndexTTS 2.0/2.5 offline inference")
-    parser.add_argument(
-        "--model",
-        required=True,
-        help="HF model path or native bundle containing checkpoints/.",
-    )
-    parser.add_argument(
-        "--model-version",
-        choices=("2.0", "2.5"),
-        default="2.0",
-    )
-    parser.add_argument(
-        "--lang",
-        default="zh",
-        help=(
-            "IndexTTS 2.5 language code, for example zh/en/zhen/ja/yue; "
-            "zhen is mixed Chinese/English and Mandarin is a vLLM-Omni alias for zh."
-        ),
-    )
-    parser.add_argument(
-        "--no-text-normalization",
-        action="store_false",
-        dest="text_normalization",
-        help="Disable IndexTTS 2.5 text normalization.",
-    )
-    parser.add_argument(
-        "--speed",
-        type=float,
-        default=1.0,
-        help="IndexTTS 2.5 native synthesis speed in [0.5, 2.0]; 2.0 is faster.",
-    )
+    parser = FlexibleArgumentParser(description="IndexTTS2 offline inference")
+    parser.add_argument("--model", required=True, help="HF model path for IndexTTS2.")
     parser.add_argument("--text", default="你好，这是IndexTTS2语音合成测试。")
     parser.add_argument("--ref-audio", required=True, help="Reference audio for voice cloning.")
     parser.add_argument("--emo-audio", default=None, help="Emotion reference audio.")
@@ -253,15 +170,7 @@ def parse_args():
     parser.add_argument("--emo-alpha", type=float, default=None, help="Emotion weight in [0, 1].")
     parser.add_argument("--use-emo-text", action="store_true", help="Infer emotion vector from emo-text or text.")
     parser.add_argument("--use-random", action="store_true", help="Use random emotion prototypes.")
-    parser.add_argument(
-        "--seed",
-        type=int,
-        default=None,
-        help=(
-            "Seed Stage 0 AR sampling and per-request CFM noise; changing the "
-            "concurrent batch composition may still change the final waveform."
-        ),
-    )
+    parser.add_argument("--seed", type=int, default=None)
     parser.add_argument(
         "--output-dir",
         default=os.path.join(
@@ -271,10 +180,7 @@ def parse_args():
     )
     parser.add_argument("--deploy-config", default=None)
     parser.add_argument("--stage-init-timeout", type=int, default=600)
-    args = parser.parse_args()
-    if args.model_version == "2.5" and not 0.5 <= args.speed <= 2.0:
-        parser.error("IndexTTS 2.5 --speed must be between 0.5 and 2.0")
-    return args
+    return parser.parse_args()
 
 
 if __name__ == "__main__":

examples/offline_inference/text_to_video/text_to_video.md

@@ -55,21 +55,6 @@ python text_to_video.py \
   --output vace_t2v_output.mp4
 ```
 
-### LingBot-Video
-
-The dedicated LingBot example explicitly selects the video output modality:
-
-```bash
-python examples/offline_inference/text_to_video/text_to_video_lingbot.py \
-  --model robbyant/lingbot-video-dense-1.3b \
-  --height 192 --width 320 --num-frames 9 --num-inference-steps 2 \
-  --output lingbot_t2v.mp4
-```
-
-Use the same command with `robbyant/lingbot-video-moe-30b-a3b` for the MoE
-checkpoint. Requested frame counts are rounded upward to the causal
-VAE's `4n+1` grid.
-
 ### LTX-2
 
 ```bash
@@ -218,9 +203,6 @@ python text_to_video.py \
 - `--audio-sample-rate`: fallback audio sample rate when the pipeline returns audio.
 - `--quantization`: quantization method (such as `fp8` for FP8).
 - `--flow-shift`: scheduler flow_shift parameter.
-- `--lora-path`: path to PEFT LoRA adapter folder or checkpoint file.
-- `--lora-scale`: scale factor for LoRA weights.
-- `--lora-backend`: backend for loading LoRA adapters. Default: peft. Available options: peft, distill.
 - `--extra-body`: JSON object of model-specific generation params, filtered against the model's declared `extra_body_params` (see [`vllm_omni/model_extras`](../../../vllm_omni/model_extras)). Used by Cosmos3 (see above).
 
 ### Wan2.2-specific

examples/offline_inference/text_to_video/text_to_video.py

@@ -14,8 +14,6 @@ from vllm_omni.diffusion.data import DiffusionParallelConfig
 from vllm_omni.diffusion.utils.param_utils import apply_declared_extra_args
 from vllm_omni.entrypoints.omni import Omni
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-from vllm_omni.lora.request import LoRARequest
-from vllm_omni.lora.utils import stable_lora_int_id
 from vllm_omni.model_extras import get_extra_body_params, get_model_class_name
 from vllm_omni.outputs import OmniRequestOutput
 from vllm_omni.platforms import current_omni_platform
@@ -336,29 +334,6 @@ def parse_args() -> argparse.Namespace:
         action="store_true",
         help="Enable expert parallelism for MoE layers.",
     )
-    parser.add_argument(
-        "--lora-path",
-        type=str,
-        nargs="+",
-        default=None,
-        help="Path to LoRA adapter folder (PEFT format) or concrete LoRA checkpoint files. Loaded at initialization and used for generation."
-        "Note: for Wan2.2 MoE models, two checkpoints positionally mapped to high-noise and low-noise modules.",
-    )
-    parser.add_argument(
-        "--lora-scale",
-        type=float,
-        default=1.0,
-        help="Scale factor for LoRA weights (default: 1.0).",
-    )
-    parser.add_argument(
-        "--lora-backend",
-        type=str,
-        default="peft",
-        choices=["peft", "distill"],
-        help="LoRA backend for loading LoRA adapters. Default: peft"
-        "'peft' loads a PEFT-format adapter folder, used e.g. for RL"
-        "'distill' fuses one or more concrete LoRA checkpoint files, used e.g. for distilled few-step LoRAs",
-    )
     parser.add_argument(
         "--use-hsdp",
         action="store_true",
@@ -465,12 +440,6 @@ def main():
         omni_kwargs["cache_backend"] = args.cache_backend
         omni_kwargs["cache_config"] = cache_config
         omni_kwargs["enable_cache_dit_summary"] = args.enable_cache_dit_summary
-    if args.lora_path is not None:
-        lora_path = args.lora_path
-        if len(lora_path) == 1:
-            lora_path = lora_path[0]
-        omni_kwargs["lora_path"] = lora_path
-        omni_kwargs["lora_backend"] = args.lora_backend
 
     # Cosmos3 loads its (gated) guardrail models at build time, so the guardrails
     # gate is an engine-level config (offline analog of the server's --no-guardrails).
@@ -500,19 +469,6 @@ def main():
     print(f"  Video size: {args.width}x{args.height}")
     print(f"{'=' * 60}\n")
 
-    lora_request = None
-    if args.lora_path and args.lora_backend == "peft":
-        if len(args.lora_path) != 1:
-            raise ValueError("Only one LoRA path is expected for PEFT backend.")
-
-        lora_path = args.lora_path[0]
-        lora_request_id = stable_lora_int_id(lora_path)
-        lora_request = LoRARequest(
-            lora_name=Path(lora_path).stem,
-            lora_int_id=lora_request_id,
-            lora_path=lora_path,
-        )
-
     prompt_dict = {"prompt": args.prompt}
     if args.negative_prompt is not None:
         prompt_dict["negative_prompt"] = args.negative_prompt
@@ -520,11 +476,6 @@ def main():
         # Preserve the historical empty-prompt behavior for non-LTX examples.
         prompt_dict["negative_prompt"] = ""
 
-    extra_args = {}
-    if lora_request:
-        extra_args["lora_request"] = lora_request
-        extra_args["lora_scale"] = args.lora_scale
-
     sampling_kwargs = dict(
         height=args.height,
         width=args.width,
@@ -532,7 +483,6 @@ def main():
         guidance_scale=args.guidance_scale,
         num_inference_steps=args.num_inference_steps,
         num_frames=args.num_frames,
-        extra_args=extra_args,
     )
     if args.guidance_scale_high is not None:
         sampling_kwargs["guidance_scale_2"] = args.guidance_scale_high

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="robbyant/lingbot-video-dense-1.3b")
+    parser.add_argument("--model", default="/home/models/lingbot-video-dense-1.3b")
     parser.add_argument("--prompt", default="a robotic arm picks up a red block")
-    parser.add_argument("--negative-prompt", default=None)
+    parser.add_argument("--negative-prompt", default="")
     parser.add_argument("--output", default="lingbot_video_output.mp4")
     parser.add_argument("--height", type=int, default=192)
     parser.add_argument("--width", type=int, default=320)
@@ -58,12 +58,9 @@ def _to_frame_array(video: Any) -> np.ndarray:
     if isinstance(video, torch.Tensor):
         tensor = video.detach().cpu()
         if tensor.dim() == 5:
-            tensor = tensor[0]
-        if tensor.dim() == 4 and tensor.shape[-1] not in (3, 4):
-            if tensor.shape[0] in (3, 4):
-                tensor = tensor.permute(1, 2, 3, 0)
-            elif tensor.shape[1] in (3, 4):
-                tensor = tensor.permute(0, 2, 3, 1)
+            tensor = tensor[0] if tensor.shape[1] not in (3, 4) else tensor[0].permute(1, 2, 3, 0)
+        elif tensor.dim() == 4 and tensor.shape[0] in (3, 4):
+            tensor = tensor.permute(1, 2, 3, 0)
         if tensor.is_floating_point():
             if float(tensor.min()) < 0.0:
                 tensor = tensor.clamp(-1, 1) * 0.5 + 0.5
@@ -90,12 +87,8 @@ def main() -> None:
         parallel_config=DiffusionParallelConfig(),
     )
 
-    prompt: dict[str, Any] = {
-        "prompt": args.prompt,
-        "modalities": ["video"],
-        "num_frames": args.num_frames,
-    }
-    if args.negative_prompt is not None:
+    prompt: dict[str, str] = {"prompt": args.prompt}
+    if args.negative_prompt:
         prompt["negative_prompt"] = args.negative_prompt
 
     sampling_params = OmniDiffusionSamplingParams(

examples/online_serving/image_to_video/README.md

@@ -1,9 +1,6 @@
 # Image-To-Video
 
-This example demonstrates online image-to-video generation with vLLM-Omni.
-The startup script defaults to Wan2.2, but `MODEL` can select any supported
-image-to-video model. The existing curl helper remains a concrete Wan2.2
-request through the standard Videos API.
+This example demonstrates how to deploy the Wan2.2 image-to-video model for online video generation using vLLM-Omni.
 
 ## Start Server
 
@@ -23,7 +20,9 @@ bash run_server.sh
 
 The script allows overriding:
 - `MODEL` (default: `Wan-AI/Wan2.2-I2V-A14B-Diffusers`)
-- `PORT` (default: `8099`)
+- `PORT` (default: `8091`)
+- `BOUNDARY_RATIO` (default: `0.875`)
+- `FLOW_SHIFT` (default: `12.0`)
 - `CACHE_BACKEND` (default: `none`)
 - `ENABLE_CACHE_DIT_SUMMARY` (default: `0`)
 

examples/online_serving/image_to_video/run_server.sh

@@ -1,12 +1,12 @@
 #!/bin/bash
-# Shared image-to-video server start script
+# Wan2.2 image-to-video server start script
 
 MODEL="${MODEL:-Wan-AI/Wan2.2-I2V-A14B-Diffusers}"
 PORT="${PORT:-8099}"
 CACHE_BACKEND="${CACHE_BACKEND:-none}"
 ENABLE_CACHE_DIT_SUMMARY="${ENABLE_CACHE_DIT_SUMMARY:-0}"
 
-echo "Starting image-to-video server..."
+echo "Starting Wan2.2 I2V server..."
 echo "Model: $MODEL"
 echo "Port: $PORT"
 echo "Cache backend: $CACHE_BACKEND"

examples/online_serving/lingbot_video/README.md

@@ -1,74 +0,0 @@
-# LingBot-Video
-
-LingBot-Video uses one `LingBotVideoPipeline` for text-to-image (T2I),
-text-to-video (T2V), and text-image-to-video (TI2V) generation. Both the dense
-and MoE checkpoints use the same request format.
-
-## Start the server
-
-```bash
-MODEL=robbyant/lingbot-video-dense-1.3b bash run_server.sh
-```
-
-The MoE checkpoint uses the same server and request scripts, but requires
-substantially more GPU memory:
-
-```bash
-MODEL=robbyant/lingbot-video-moe-30b-a3b bash run_server.sh
-```
-
-## Text to image
-
-The image endpoint selects T2I mode and always generates one frame:
-
-```bash
-bash run_curl_text_to_image.sh
-```
-
-The script sends a `320x192`, two-step smoke request and writes
-`lingbot_t2i.png`.
-
-## Text or text-image to video
-
-Run the video script without an image to select T2V mode:
-
-```bash
-bash run_curl_text_image_to_video.sh
-```
-
-Pass a first-frame image to the same script to select TI2V mode:
-
-```bash
-INPUT_IMAGE=/path/to/input.png bash run_curl_text_image_to_video.sh
-```
-
-The client scripts omit the optional `model` request field, so they target
-whichever dense or MoE checkpoint the server loaded. The video example uses the
-lightweight `320x192`, 9-frame, two-step configuration.
-
-Until the shared `/v1/videos` reference-image resizing is removed, TI2V target
-dimensions must be sent through `extra_params`, for example
-`{"size":"320x192"}`. Do not use the top-level `size`, `width`, or `height`
-fields for TI2V because the serving layer currently applies those dimensions
-to the reference image before the model receives it. T2V requests can continue
-to use the top-level dimension fields.
-
-LingBot video frame counts use the causal VAE `4n+1` grid. The pipeline rounds
-any requested frame count upward to the next valid value. An explicit
-`num_frames` takes precedence over `seconds`; otherwise, the server first
-resolves `seconds * fps` and the pipeline applies the same alignment.
-
-Official `resolution`/`ratio` presets can be sent through `extra_params`, for
-example `{"resolution":"720p","ratio":"16:9"}`. The `2k` and `4k` entries
-only define output dimensions; whether they run successfully depends on the
-checkpoint, GPU memory, and memory optimizations available in the deployment.
-
-For `/v1/images/generations`, the server resolves these aliases to their final
-pixel dimensions before applying `--max-generated-image-size`. Requests above
-the configured limit return HTTP 400 before engine dispatch. LingBot produces
-one output per prompt; image requests with `n>1` are also rejected with HTTP
-400.
-
-LingBot TI2V accepts exactly one image reference. Image editing, video
-references, audio references, batching, and Refiner execution are not supported
-by this pipeline mode.

examples/online_serving/lingbot_video/run_curl_text_image_to_video.sh

@@ -1,67 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-if [ -n "${INPUT_IMAGE:-}" ] && [ ! -f "${INPUT_IMAGE}" ]; then
-    echo "INPUT_IMAGE does not exist: ${INPUT_IMAGE}"
-    exit 1
-fi
-
-BASE_URL="${BASE_URL:-http://localhost:8099}"
-POLL_INTERVAL="${POLL_INTERVAL:-2}"
-
-if [ -n "${INPUT_IMAGE:-}" ]; then
-    default_output="lingbot_ti2v.mp4"
-else
-    default_output="lingbot_t2v.mp4"
-fi
-OUTPUT_PATH="${OUTPUT_PATH:-${default_output}}"
-
-curl_args=(
-    -sS -X POST "${BASE_URL}/v1/videos"
-    -H "Accept: application/json"
-    -F "prompt=the subject turns toward the camera with smooth natural motion"
-    -F "num_frames=9"
-    -F "fps=24"
-    -F "num_inference_steps=2"
-    -F "guidance_scale=3.0"
-    -F "flow_shift=3.0"
-    -F "seed=42"
-)
-if [ -n "${INPUT_IMAGE:-}" ]; then
-    curl_args+=(
-        -F "input_reference=@${INPUT_IMAGE}"
-        -F 'extra_params={"size":"320x192"}'
-    )
-else
-    curl_args+=(-F "width=320" -F "height=192")
-fi
-
-create_response="$(curl "${curl_args[@]}")"
-
-video_id="$(echo "${create_response}" | jq -er '.id')"
-echo "Created video job ${video_id}"
-
-while true; do
-    status_response="$(curl -sS "${BASE_URL}/v1/videos/${video_id}")"
-    status="$(echo "${status_response}" | jq -er '.status')"
-    case "${status}" in
-        queued|in_progress)
-            sleep "${POLL_INTERVAL}"
-            ;;
-        completed)
-            break
-            ;;
-        failed)
-            echo "${status_response}" | jq .
-            exit 1
-            ;;
-        *)
-            echo "Unexpected video job status: ${status}"
-            exit 1
-            ;;
-    esac
-done
-
-curl -sS -L "${BASE_URL}/v1/videos/${video_id}/content" -o "${OUTPUT_PATH}"
-echo "Saved video to ${OUTPUT_PATH}"

examples/online_serving/lingbot_video/run_curl_text_to_image.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-BASE_URL="${BASE_URL:-http://localhost:8099}"
-OUTPUT_PATH="${OUTPUT_PATH:-lingbot_t2i.png}"
-
-curl -sS -X POST "${BASE_URL}/v1/images/generations" \
-    -H "Content-Type: application/json" \
-    -d "{
-        \"prompt\": \"a red fox standing in fresh snow\",
-        \"size\": \"320x192\",
-        \"num_inference_steps\": 2,
-        \"guidance_scale\": 3.0,
-        \"flow_shift\": 3.0,
-        \"seed\": 42,
-        \"response_format\": \"b64_json\"
-    }" | jq -er '.data[0].b64_json' | base64 -d > "${OUTPUT_PATH}"
-
-echo "Saved image to ${OUTPUT_PATH}"

examples/online_serving/lingbot_video/run_server.sh

@@ -1,10 +0,0 @@
-#!/bin/bash
-
-set -euo pipefail
-
-MODEL="${MODEL:-robbyant/lingbot-video-dense-1.3b}"
-PORT="${PORT:-8099}"
-
-vllm serve "${MODEL}" --omni \
-    --model-class-name LingBotVideoPipeline \
-    --port "${PORT}"

examples/online_serving/minicpmo/README.md

@@ -23,10 +23,10 @@ including `librosa`.
 
 The deploy config auto-loads via `--omni`.
 The default `vllm_omni/deploy/minicpmo_4_5.yaml` keeps all three stages on
-logical device 0 with memory budgets of 55%, 15%, and 18%, leaving headroom
+logical device 0 with memory budgets of 55%, 15%, and 15%, leaving headroom
 for runtime kernels such as the HiFi-GAN vocoder's cuDNN workspace. The
-profile admits at most four sequences per stage and bounds Talker context
-to 4096 tokens. For throughput,
+profile admits at most four sequences per stage and bounds startup video
+profiling to 32 frames per video. For throughput,
 `minicpmo_4_5_2gpu.yaml` gives the Thinker
 GPU 0 (90%) and colocates the Talker (55%) and Code2Wav (35%) on GPU 1. That
 profile admits at most four concurrent sequences per stage.

examples/online_serving/minicpmo/realtime_duplex_demo.py

@@ -196,7 +196,6 @@ async def run_demo(args: argparse.Namespace) -> dict[str, object]:
             args.model,
             ref_audio=_ref_audio_data_url(args.ref_audio),
             session_id=args.session_id,
-            temperature=args.temperature,
             timeout_s=args.timeout_s,
         )
         stream_event_cursor = len(client.events.events)
@@ -384,12 +383,6 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--output-dir", default="/tmp/minicpmo_realtime_duplex_demo")
     parser.add_argument("--chunk-ms", type=int, default=200)
     parser.add_argument("--timeout-s", type=float, default=60.0)
-    parser.add_argument(
-        "--temperature",
-        type=float,
-        default=None,
-        help="Stage0 sampling temperature; response-required soft-interrupt uses 0.0.",
-    )
     parser.add_argument("--no-realtime-pacing", action="store_true")
     parser.add_argument("--require-audio", action="store_true")
     return parser.parse_args()

examples/online_serving/text_to_image/README.md

@@ -1,9 +1,6 @@
 # Text-To-Image
 
-This example demonstrates online text-to-image generation with vLLM-Omni. The
-startup script and Python clients default to Qwen-Image, but `MODEL` can select
-any supported text-to-image model. The existing curl helper remains a concrete
-Qwen-Image request through the standard Images API.
+This example demonstrates how to deploy Qwen-Image model for online image generation service using vLLM-Omni.
 
 ## Start Server
 
@@ -118,23 +115,7 @@ python gradio_demo.py
 
 ## LoRA
 
-This example supports both startup-time distilled LoRAs and request-time
-PEFT-compatible adapters. The LoRA path must be readable on the **server**
-machine (usually a local path or a mounted directory).
-
-### Start Server with a Distilled LoRA
-
-```bash
-vllm serve Qwen/Qwen-Image-2512 \
-  --omni \
-  --port 8091 \
-  --lora-backend distill \
-  --lora-path /path/to/Qwen-Image-2512-Lightning-4steps.safetensors
-```
-
-The distilled LoRA is fused once during server initialization and applies to
-every request. Use the checkpoint's few-step sampling settings, for example
-`num_inference_steps=4` and `true_cfg_scale=1.0`.
+This example supports Peft-compatible LoRA (Low-Rank Adaptation) adapters for diffusion models. The LoRA adapter path must be readable on the **server** machine (usually a local path or a mounted directory).
 
 ### Using Python Client with LoRA
 
@@ -245,8 +226,8 @@ count, use `size` and `n` rather than `height`, `width`, or
 | `height`                 | int   | None    | Image height in pixels         |
 | `width`                  | int   | None    | Image width in pixels          |
 | `size`                   | str   | None    | Image size (e.g., "1024x1024") |
-| `num_inference_steps`    | int   | model   | Number of denoising steps      |
-| `true_cfg_scale`         | float | model   | True CFG scale when supported  |
+| `num_inference_steps`    | int   | 50      | Number of denoising steps      |
+| `true_cfg_scale`         | float | 4.0     | Qwen-Image CFG scale           |
 | `seed`                   | int   | None    | Random seed (reproducible)     |
 | `negative_prompt`        | str   | None    | Negative prompt                |
 | `num_outputs_per_prompt` | int   | 1       | Number of images to generate   |

examples/online_serving/text_to_image/gradio_demo.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Shared text-to-image Gradio demo for online serving.
+Qwen-Image Gradio Demo for online serving.
 
 Usage:
     python gradio_demo.py [--server http://localhost:8091] [--port 7860]
@@ -77,9 +77,9 @@ def generate_image(
 def create_demo(server_url: str):
     """Create Gradio demo interface."""
 
-    with gr.Blocks(title="Text-to-Image Demo") as demo:
-        gr.Markdown("# Text-to-Image Online Generation")
-        gr.Markdown("Generate images using the model configured on the server")
+    with gr.Blocks(title="Qwen-Image Demo") as demo:
+        gr.Markdown("# Qwen-Image Online Generation")
+        gr.Markdown("Generate images using Qwen-Image model")
 
         with gr.Row():
             with gr.Column(scale=1):
@@ -115,6 +115,7 @@ def create_demo(server_url: str):
                         label="Inference Steps",
                         minimum=10,
                         maximum=100,
+                        # Default steps aligned with run_curl_text_to_image.sh to 100
                         value=100,
                         step=5,
                     )
@@ -172,7 +173,7 @@ def create_demo(server_url: str):
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Shared text-to-image Gradio demo")
+    parser = argparse.ArgumentParser(description="Qwen-Image Gradio Demo")
     parser.add_argument("--server", default="http://localhost:8091", help="Server URL")
     parser.add_argument("--port", type=int, default=7860, help="Gradio port")
     parser.add_argument("--share", action="store_true", help="Create public link")

examples/online_serving/text_to_image/openai_chat_client.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Shared OpenAI-compatible text-to-image generation client.
+Qwen-Image OpenAI-compatible image generation client.
 
 Usage:
     python openai_chat_client.py --prompt "A beautiful landscape" --output output.png
@@ -39,7 +39,7 @@ def generate_image(
         height: Image height in pixels
         width: Image width in pixels
         steps: Number of diffusion steps
-        true_cfg_scale: True CFG scale for models that support it
+        true_cfg_scale: Qwen-Image CFG scale
         seed: Random seed
         negative_prompt: Negative prompt
         num_outputs_per_prompt: Number of images to generate
@@ -70,7 +70,7 @@ def generate_image(
         payload["num_inference_steps"] = steps
     if true_cfg_scale is not None:
         payload["true_cfg_scale"] = true_cfg_scale
-    if negative_prompt is not None:
+    if negative_prompt:
         payload["negative_prompt"] = negative_prompt
     if seed is not None:
         payload["seed"] = seed
@@ -115,15 +115,15 @@ def generate_image(
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Shared text-to-image client")
+    parser = argparse.ArgumentParser(description="Qwen-Image chat client")
     parser.add_argument("--prompt", "-p", default="a cup of coffee on the table", help="Text prompt")
-    parser.add_argument("--output", "-o", default="text_to_image_output.png", help="Output file")
+    parser.add_argument("--output", "-o", default="qwen_image_output.png", help="Output file")
     parser.add_argument("--server", "-s", default="http://localhost:8091", help="Server URL")
-    parser.add_argument("--height", type=int, help="Image height; defaults to the model setting")
-    parser.add_argument("--width", type=int, help="Image width; defaults to the model setting")
-    parser.add_argument("--steps", type=int, help="Inference steps; defaults to the model setting")
-    parser.add_argument("--cfg-scale", type=float, help="True CFG scale when supported")
-    parser.add_argument("--seed", type=int, help="Random seed")
+    parser.add_argument("--height", type=int, default=1024, help="Image height")
+    parser.add_argument("--width", type=int, default=1024, help="Image width")
+    parser.add_argument("--steps", type=int, default=50, help="Inference steps")
+    parser.add_argument("--cfg-scale", type=float, default=4.0, help="True CFG scale")
+    parser.add_argument("--seed", type=int, default=0, help="Random seed")
     parser.add_argument("--negative", help="Negative prompt")
 
     parser.add_argument("--lora-path", default=None, help="Server-local LoRA adapter folder (PEFT format)")

examples/online_serving/text_to_image/run_server.sh

@@ -1,10 +1,10 @@
 #!/bin/bash
-# Shared text-to-image online serving startup script
+# Qwen-Image online serving startup script
 
 MODEL="${MODEL:-Qwen/Qwen-Image}"
 PORT="${PORT:-8091}"
 
-echo "Starting text-to-image server..."
+echo "Starting Qwen-Image server..."
 echo "Model: $MODEL"
 echo "Port: $PORT"
 

examples/online_serving/text_to_speech/README.md

@@ -16,8 +16,7 @@ For the full list of supported architectures across all modalities, see
 |---|---|---|---|---|---|
 | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✓ (`ref_audio`+`ref_text`) | ✓ (PCM stream) | — | ✓ |
 | GLM-TTS | `zai-org/GLM-TTS` | ✓ (`ref_audio`+`ref_text`, required) | ✓ (PCM stream) | — | ✓ |
-| IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✓ (`ref_audio` or uploaded `voice`) | `stream=true` response, non-chunk | uploaded audio voice only; no presets | — |
-| IndexTTS-2.5 | native `checkpoints/` bundle | ✓ (`ref_audio` or uploaded `voice`) | `stream=true` response, non-chunk | uploaded audio voice only; no presets | — |
+| IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✓ (`ref_audio` or uploaded `voice`) | compat only, non-chunk | uploaded audio voice only; no presets | — |
 | Ming-omni-tts | `inclusionAI/Ming-omni-tts-0.5B` | ✓ (`ref_audio` / `speaker_embedding`) | ✓ (PCM stream) | IP labels + structured `instructions` | — |
 | Ming-flash-omni-TTS | `Jonathan1909/Ming-flash-omni-2.0` | — (caption-controlled) | — | caption fields (`instructions`) | — |
 | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✓ (`ref_audio` required) | ✓ (PCM stream) | — | ✓ |
@@ -139,29 +138,15 @@ bash examples/online_serving/text_to_speech/glm_tts/run_gradio_demo.sh
 
 ---
 
-## IndexTTS-2 and IndexTTS-2.5
+## IndexTTS-2
 
-2-stage TTS at 22.05 kHz. Requests use `ref_audio` for voice cloning, or an uploaded audio `voice` from `/v1/audio/voices`. IndexTTS-2.5 uses a multilingual tokenizer, CAMPPlus speaker projection, EnhancedCodec, and code-only Stage 0→1 transfer by default. Both versions support emotion conditioning via `emo_audio`, `emo_text`, or `emo_vector` passed in `extra_params`.
-
-### Prerequisites
-
-IndexTTS-2 uses its existing frontend and does not require the IndexTTS-2.5 text dependencies. Before launching IndexTTS-2.5, install its optional frontend dependencies:
-
-```bash
-pip install 'vllm-omni[indextts2]'
-```
+2-stage TTS (GPT AR + S2Mel CFM DiT + BigVGAN) at 22.05 kHz. Requests use `ref_audio` for voice cloning, or an uploaded audio `voice` from `/v1/audio/voices`. Supports emotion conditioning via `emo_audio`, `emo_text`, or `emo_vector` passed in `extra_params`.
 
 ### Launch
 ```bash
 vllm serve IndexTeam/IndexTTS-2 --omni --trust-remote-code --port 8092
 # or, to pass the bundled deploy config explicitly:
 bash examples/online_serving/text_to_speech/indextts2/run_server.sh
-
-# IndexTTS-2.5 default: use_gpt_latent=false
-MODEL_VERSION=2.5 \
-MODEL=/path/to/indextts-2.5 \
-bash examples/online_serving/text_to_speech/indextts2/run_server.sh
-
 ```
 
 ### Sending requests
@@ -176,35 +161,14 @@ python examples/online_serving/text_to_speech/indextts2/speech_client.py \
     --text "今天心情很好！" \
     --ref-audio /path/to/ref.wav \
     --emo-audio /path/to/happy.wav
-
-# IndexTTS-2.5 Japanese request
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-    --model-version 2.5 \
-    --model /path/to/indextts-2.5 \
-    --lang ja \
-    --text "こんにちは、音声合成のテストです。" \
-    --ref-audio /path/to/ref.wav
-
-# IndexTTS-2.5 native speed control
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-    --model-version 2.5 \
-    --model /path/to/indextts-2.5 \
-    --speed 2.0 \
-    --text "这是两倍速度的语音合成测试。" \
-    --ref-audio /path/to/ref.wav
 ```
 
 ### Notes
 - Output: 22.05 kHz mono WAV.
-- Provide `ref_audio` on the documented raw request path, or pass `voice` only when it names an uploaded audio voice; neither version provides a built-in text-only preset voice.
-- IndexTTS-2.5 request controls `lang` and `text_normalization` are carried in `extra_params`; the client does this for `--model-version 2.5`.
-- IndexTTS-2.5 accepts the public `speed` request field in `[0.5, 2.0]`: `2.0` generates shorter, faster speech and `0.5` generates longer, slower speech. This is native Stage 1 duration control, so serving does not apply the generic playback-speed adjustment a second time. IndexTTS-2 does not use this control.
-- IndexTTS-2.5 accepts language codes such as `zh`, `en`, `zhen` (mixed Chinese/English), `ja`, and `yue`. `Mandarin` is a vLLM-Omni convenience alias for `zh`. Japanese (`ja`) uses `fugashi` tokenization and produces audio, but it does not automatically expand numbers, dates, or percentages; callers should first write those inputs as readable Japanese text.
-- A request `seed` controls Stage 0 AR sampling and per-request CFM noise. Different concurrent batch compositions do not guarantee a bit-identical waveform.
-- IndexTTS-2.5 Stage 0 uses plain vLLM sampling and does not reproduce the official default `num_beams=3` beam search. For parity comparisons, run upstream with `num_beams=1`; output quality can differ from the official beam-search result.
+- Provide `ref_audio` on the documented raw request path, or pass `voice` only when it names an uploaded audio voice; IndexTTS-2 does not provide a built-in text-only preset voice.
 - Emotion params (`emo_audio`, `emo_text`, `emo_vector`, `emo_alpha`, `use_emo_text`, `use_random`) are passed via the `extra_params` field. Official precedence is `use_emo_text` > `emo_vector` > `emo_audio` > same emotion as the speaker reference.
-- IndexTTS-2.5 uses `vllm_omni/deploy/indextts2_5.yaml` with the official code-only Stage 0 to Stage 1 contract.
-- For IndexTTS-2.5, set `MODEL` to the local native bundle; asset discovery accepts its nested `checkpoints/` layout.
+- `stream=true` is accepted as an OpenAI-compatible response path, but IndexTTS-2 is not async-chunk streaming; audio is produced after S2Mel receives the full mel-code sequence.
+- Deploy config: `vllm_omni/deploy/indextts2.yaml` (auto-loaded).
 
 ---
 

examples/online_serving/text_to_speech/indextts2/run_server.sh

@@ -1,37 +1,20 @@
 #!/bin/bash
-# Launch vLLM-Omni server for IndexTTS 2.0 or 2.5.
+# Launch vLLM-Omni server for IndexTTS2
 #
 # Usage from repository root:
 #   examples/online_serving/text_to_speech/indextts2/run_server.sh
-#   MODEL_VERSION=2.5 MODEL=/path/to/native/bundle \
-#     examples/online_serving/text_to_speech/indextts2/run_server.sh
+#   CUDA_VISIBLE_DEVICES=0 PORT=8092 MODEL=/path/to/IndexTeam/IndexTTS-2 examples/online_serving/text_to_speech/indextts2/run_server.sh
 
 set -e
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
 ROOT_DIR="$(cd -- "$SCRIPT_DIR/../../../.." && pwd)"
 
-MODEL_VERSION="${MODEL_VERSION:-2.0}"
+MODEL="${MODEL:-IndexTeam/IndexTTS-2}"
 PORT="${PORT:-8092}"
+DEPLOY_CONFIG="${DEPLOY_CONFIG:-$ROOT_DIR/vllm_omni/deploy/indextts2.yaml}"
 
-if [[ "$MODEL_VERSION" == "2.5" ]]; then
-    if [[ -z "${MODEL:-}" ]]; then
-        echo "Usage: MODEL_VERSION=2.5 MODEL=/path/to/native/bundle bash $0" >&2
-        exit 2
-    fi
-    DEFAULT_DEPLOY_CONFIG="$ROOT_DIR/vllm_omni/deploy/indextts2_5.yaml"
-elif [[ "$MODEL_VERSION" == "2.0" ]]; then
-    MODEL="${MODEL:-IndexTeam/IndexTTS-2}"
-    DEFAULT_DEPLOY_CONFIG="$ROOT_DIR/vllm_omni/deploy/indextts2.yaml"
-else
-    echo "MODEL_VERSION must be 2.0 or 2.5" >&2
-    exit 2
-fi
-
-DEPLOY_CONFIG="${DEPLOY_CONFIG:-$DEFAULT_DEPLOY_CONFIG}"
-
-echo "Starting IndexTTS $MODEL_VERSION server with model: $MODEL"
-echo "Deploy config: $DEPLOY_CONFIG"
+echo "Starting IndexTTS2 server with model: $MODEL"
 
 FLASHINFER_DISABLE_VERSION_CHECK=1 \
 vllm serve "$MODEL" \

examples/online_serving/text_to_speech/indextts2/speech_client.py

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""OpenAI-compatible client for IndexTTS 2.0/2.5 via /v1/audio/speech.
+"""OpenAI-compatible client for IndexTTS2 TTS via /v1/audio/speech endpoint.
 
 Examples:
     # With reference audio for voice cloning
@@ -54,44 +54,13 @@ def main() -> None:
     parser.add_argument("--emo-alpha", type=float, default=None, help="Emotion weight in [0, 1]")
     parser.add_argument("--use-emo-text", action="store_true", help="Infer emotion vector from emo-text or text")
     parser.add_argument("--use-random", action="store_true", help="Use random emotion prototypes")
-    parser.add_argument(
-        "--model-version",
-        choices=("2.0", "2.5"),
-        default="2.0",
-    )
-    parser.add_argument("--model", type=str, default=None)
-    parser.add_argument(
-        "--lang",
-        default="zh",
-        help=(
-            "IndexTTS 2.5 language code, for example zh/en/zhen/ja/yue; "
-            "zhen is mixed Chinese/English and Mandarin is a vLLM-Omni alias for zh"
-        ),
-    )
-    parser.add_argument(
-        "--no-text-normalization",
-        action="store_false",
-        dest="text_normalization",
-        help="Disable IndexTTS 2.5 text normalization",
-    )
-    parser.add_argument(
-        "--speed",
-        type=float,
-        default=1.0,
-        help="IndexTTS 2.5 native synthesis speed in [0.5, 2.0]; 2.0 is faster",
-    )
+    parser.add_argument("--model", type=str, default="IndexTeam/IndexTTS-2")
     parser.add_argument("--voice", type=str, default=None, help="Uploaded voice name to use instead of --ref-audio")
     parser.add_argument("--output", type=str, default="output.wav")
     parser.add_argument("--api-base", type=str, default=DEFAULT_API_BASE)
     parser.add_argument("--api-key", type=str, default=DEFAULT_API_KEY)
     parser.add_argument("--response-format", type=str, default="wav")
     args = parser.parse_args()
-    if args.model is None:
-        if args.model_version == "2.5":
-            parser.error("--model is required for IndexTTS 2.5")
-        args.model = "IndexTeam/IndexTTS-2"
-    if args.model_version == "2.5" and not 0.5 <= args.speed <= 2.0:
-        parser.error("IndexTTS 2.5 --speed must be between 0.5 and 2.0")
 
     if not args.ref_audio and not args.voice:
         parser.error("IndexTTS2 requires --ref-audio or --voice for voice cloning")
@@ -128,10 +97,6 @@ def main() -> None:
         extra_params["use_emo_text"] = True
     if args.use_random:
         extra_params["use_random"] = True
-    if args.model_version == "2.5":
-        payload["speed"] = args.speed
-        extra_params["lang"] = args.lang
-        extra_params["text_normalization"] = args.text_normalization
     if extra_params:
         payload["extra_params"] = extra_params
 

examples/quantization/check_modelopt_fp8_export.py

@@ -0,0 +1,247 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Verify a ModelOpt FP8 diffusers checkpoint exported by
+quantize_wan2_2_modelopt_fp8.py / quantize_hunyuanvideo_15_modelopt_fp8.py.
+
+Three checks:
+  A. transformer/config.json has a sane quantization_config block.
+  B. transformer/*.safetensors contains FP8 (float8_e4m3fn) quantized tensors.
+  C. transformer disk size is materially smaller than a BF16 baseline.
+
+Example:
+    python examples/quantization/check_modelopt_fp8_export.py \\
+        --output ./hv15-480p-modelopt-fp8
+
+    # Optional: compare disk size against a local or HF BF16 baseline.
+    python examples/quantization/check_modelopt_fp8_export.py \\
+        --output ./hv15-480p-modelopt-fp8 \\
+        --baseline hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from collections import Counter
+from pathlib import Path
+
+SUPPORTED_ALGOS = ("FP8",)
+
+
+def _check_config(transformer_dir: Path) -> tuple[int, str | None]:
+    """Returns (status, quant_algo). status: 0 pass, 1 fail, 2 warn."""
+    cfg_path = transformer_dir / "config.json"
+    if not cfg_path.exists():
+        print(f"[FAIL] {cfg_path} missing.")
+        return 1, None
+
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+
+    qc = cfg.get("quantization_config")
+    if not isinstance(qc, dict):
+        print(f"[FAIL] No `quantization_config` block in {cfg_path}.")
+        return 1, None
+
+    print(f"[A] quantization_config from {cfg_path}:")
+    print(json.dumps(qc, indent=2))
+
+    quant_algo = qc.get("quant_algo")
+    issues = []
+    if qc.get("quant_method") != "modelopt":
+        issues.append(f"quant_method={qc.get('quant_method')!r} (expected 'modelopt')")
+    if quant_algo not in SUPPORTED_ALGOS:
+        issues.append(
+            f"quant_algo={quant_algo!r} (expected one of {SUPPORTED_ALGOS} — vllm-omni adapter may not auto-detect)"
+        )
+
+    if issues:
+        print("[A] WARN — config looks incomplete:")
+        for issue in issues:
+            print(f"    - {issue}")
+        return 2, quant_algo
+    print(f"[A] PASS — config looks correct (quant_algo={quant_algo}).")
+    return 0, quant_algo
+
+
+def _read_safetensors_header(path: Path) -> dict:
+    """Read the JSON header of a safetensors file. Bypass-safe — doesn't materialize tensors.
+
+    Returns {tensor_name: {'dtype': 'F8_E4M3', 'shape': [...], 'data_offsets': [...]}}.
+    Header dtype strings: F8_E4M3, F8_E5M2, BF16, F16, F32, F64, I8, I16, I32, I64, BOOL, U8, ...
+    """
+    import struct
+
+    with open(path, "rb") as f:
+        header_len = struct.unpack("<Q", f.read(8))[0]
+        header = json.loads(f.read(header_len))
+    header.pop("__metadata__", None)
+    return header
+
+
+def _classify_weight_scale_granularity(weight_scale_shapes: list[list[int]]) -> str:
+    """Infer per-tensor vs per-channel vs per-block from sample weight_scale shapes.
+
+    ModelOpt block-wise produces shapes like `[16, 1, 16, 1]` (broadcasting dims of 1
+    interleaved with block-count dims). We count "meaningful" dims — ones with size > 1 —
+    and classify: 0 meaningful dims = per-tensor (scalar), 1 = per-channel, 2+ = per-block.
+    """
+    if not weight_scale_shapes:
+        return "no weight_scale tensors found"
+
+    def meaningful_dims(shape: list[int]) -> int:
+        return sum(1 for d in shape if d > 1)
+
+    per_tensor = sum(1 for s in weight_scale_shapes if meaningful_dims(s) == 0)
+    per_channel = sum(1 for s in weight_scale_shapes if meaningful_dims(s) == 1)
+    per_block = sum(1 for s in weight_scale_shapes if meaningful_dims(s) >= 2)
+    total = len(weight_scale_shapes)
+    if per_tensor == total:
+        return "per-tensor (all scalar scales)"
+    if per_channel == total:
+        return "per-channel (1 meaningful dim)"
+    if per_block == total:
+        return "per-block (2+ meaningful dims — e.g. [M//bm, 1, N//bn, 1] for tiles)"
+    return f"mixed: per-tensor={per_tensor}, per-channel={per_channel}, per-block={per_block} of {total}"
+
+
+def _check_safetensors(transformer_dir: Path) -> int:
+    """Returns 0 on pass, 1 on fail. Reads on-disk dtype from the safetensors header."""
+    files = sorted(transformer_dir.glob("*.safetensors"))
+    if not files:
+        print(f"[FAIL] No *.safetensors in {transformer_dir}.")
+        return 1
+
+    header_dtype_counts: Counter[str] = Counter()
+    sample_quant_weight_keys: list[str] = []
+    sample_scale_keys: list[str] = []
+    weight_scale_shapes: list[list[int]] = []
+    sample_weight_scale_entries: list[tuple[str, list[int]]] = []
+
+    for f in files:
+        try:
+            header = _read_safetensors_header(f)
+        except Exception as exc:
+            print(f"[B] WARN — could not parse header of {f}: {exc}")
+            continue
+        for k, info in header.items():
+            dtype = info.get("dtype", "?")
+            header_dtype_counts[dtype] += 1
+            # FP8 stores weights as F8_E4M3 directly.
+            if dtype.startswith("F8") and k.endswith(".weight") and len(sample_quant_weight_keys) < 5:
+                sample_quant_weight_keys.append(k)
+            if k.endswith(("_scale", ".weight_scale", ".input_scale", "_scale_inv")) and len(sample_scale_keys) < 5:
+                sample_scale_keys.append(k)
+            if k.endswith(".weight_scale"):
+                weight_scale_shapes.append(info.get("shape", []))
+                if len(sample_weight_scale_entries) < 5:
+                    sample_weight_scale_entries.append((k, info.get("shape", [])))
+
+    print(f"\n[B] On-disk dtype counts across {len(files)} safetensors file(s) (from header, not get_tensor):")
+    for dtype, count in sorted(header_dtype_counts.items(), key=lambda kv: -kv[1]):
+        marker = "  <-- FP8" if dtype.startswith("F8") else ""
+        print(f"    {dtype:10s} {count:>6d}{marker}")
+
+    quant_count = sum(c for d, c in header_dtype_counts.items() if d.startswith("F8"))
+    if quant_count == 0:
+        print("[B] FAIL — no FP8 tensors on disk. Calibration likely did not actually quantize the weights.")
+        return 1
+
+    print(f"[B] PASS — {quant_count} FP8 tensors stored on disk.")
+    if sample_quant_weight_keys:
+        print(f"    sample quantized weight tensors: {sample_quant_weight_keys[:3]}")
+    if sample_scale_keys:
+        print(f"    sample scale tensors:            {sample_scale_keys[:3]}")
+    print("    (Note: torch's get_tensor() may return these as bf16 views on some versions —")
+    print("     irrelevant; vLLM's loader uses native FP8 ops.)")
+
+    # Weight-scale granularity — per-tensor (scalar) vs per-channel (1-D) vs per-block (N-D).
+    print(f"\n    weight_scale granularity: {_classify_weight_scale_granularity(weight_scale_shapes)}")
+    for key, shape in sample_weight_scale_entries[:3]:
+        print(f"      {key}: shape {shape}")
+    return 0
+
+
+def _disk_size_gib(p: Path) -> float:
+    return sum(f.stat().st_size for f in p.rglob("*") if f.is_file()) / (1024**3)
+
+
+def _check_size_vs_baseline(transformer_dir: Path, baseline: str | None) -> int:
+    """Returns 0 always (informational only)."""
+    quant_size = _disk_size_gib(transformer_dir)
+    print(f"\n[C] FP8 transformer disk size: {quant_size:.2f} GiB")
+
+    if baseline is None:
+        print("[C] SKIP — pass --baseline <path or HF id> to compare against BF16.")
+        return 0
+
+    baseline_path = Path(baseline)
+    if not baseline_path.exists():
+        # Try HF download.
+        try:
+            from huggingface_hub import snapshot_download
+        except ImportError:
+            print("[C] SKIP — huggingface_hub not installed and baseline not a local path.")
+            return 0
+        print(f"    Downloading baseline transformer from HF: {baseline}")
+        baseline_path = Path(snapshot_download(baseline, allow_patterns=["transformer/*"]))
+
+    bf16_dir = baseline_path / "transformer" if (baseline_path / "transformer").exists() else baseline_path
+    bf16_size = _disk_size_gib(bf16_dir)
+    if bf16_size == 0:
+        print(f"[C] WARN — baseline transformer dir empty: {bf16_dir}")
+        return 0
+
+    # Expected reduction for FP8: ~50%.
+    min_reduction = 30
+    reduction = (1 - quant_size / bf16_size) * 100
+    print(f"[C] BF16 baseline transformer disk size: {bf16_size:.2f} GiB ({bf16_dir})")
+    print(f"[C] Disk reduction: {reduction:.1f}%  (FP8 transformer is {quant_size / bf16_size:.0%} of BF16)")
+    if reduction < min_reduction:
+        print(
+            f"[C] WARN — FP8 should typically reduce disk by ~40-50%; <{min_reduction}% suggests partial quantization."
+        )
+    return 0
+
+
+def main() -> None:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    p.add_argument("--output", required=True, help="Path to the exported ModelOpt FP8 checkpoint root.")
+    p.add_argument(
+        "--baseline",
+        default=None,
+        help="Optional BF16 baseline (local diffusers dir or HF id) for disk-size comparison.",
+    )
+    args = p.parse_args()
+
+    out_root = Path(args.output).expanduser().resolve()
+    transformer_dir = out_root / "transformer"
+    if not transformer_dir.exists():
+        print(f"[FAIL] {transformer_dir} does not exist.")
+        sys.exit(1)
+
+    print(f"Checking: {out_root}\n")
+
+    fail = 0
+    config_status, _quant_algo = _check_config(transformer_dir)
+    fail |= config_status
+    fail |= _check_safetensors(transformer_dir)
+    _check_size_vs_baseline(transformer_dir, args.baseline)
+
+    print()
+    if fail == 0:
+        print("=" * 60)
+        print("ALL CHECKS PASSED — checkpoint looks ready for vllm-omni serving.")
+    elif fail == 1:
+        print("=" * 60)
+        print("FAILURES detected — calibration may need to be re-run.")
+        sys.exit(1)
+    else:
+        print("=" * 60)
+        print("WARNINGS only — checkpoint may serve but with caveats. See [A] above.")
+
+
+if __name__ == "__main__":
+    main()

examples/quantization/quantize_hunyuanvideo_15_modelopt_fp8.py

@@ -0,0 +1,448 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Quantize HunyuanVideo-1.5 (480p T2V) to a ModelOpt FP8 Hugging Face checkpoint.
+
+Calibrates the DiT transformer using a small video prompt set and exports a
+diffusers-style directory whose transformer carries ModelOpt FP8 metadata.
+The exported checkpoint is consumable by vllm-omni's ModelOpt FP8 adapter
+(see vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py).
+
+Layers kept full precision match the #2728 / #2795 pattern: modulation,
+AdaLayerNorm, entry/exit projections, embeddings, the token refiner path,
+and final proj_out. MHA quantizers are off by default; HV-1.5 self-attention
+empirically degrades under FP8 (see #2920 ablation).
+
+Example:
+    python examples/quantization/quantize_hunyuanvideo_15_modelopt_fp8.py \\
+        --model hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v \\
+        --output ./hv15-480p-modelopt-fp8 \\
+        --overwrite
+"""
+
+from __future__ import annotations
+
+import argparse
+import copy
+import json
+import re
+import shutil
+import sys
+from pathlib import Path
+from typing import Any
+
+import torch
+from diffusers import DiffusionPipeline
+
+DEFAULT_PROMPTS = [
+    "A dog running across a field of golden wheat.",
+    "An astronaut riding a horse across the surface of Mars, red dust swirling, cinematic wide shot.",
+    "A hummingbird hovering in front of a vibrant red flower, slow motion, macro shot.",
+    "A crackling campfire at night under a starry sky, sparks rising into the dark.",
+    "An underwater shot of a coral reef with tropical fish swimming by, sun rays piercing the water.",
+    "A close-up of a blooming rose covered in morning dew, soft natural light.",
+    "A peaceful mountain village at dawn, mist rolling over the rooftops, cinematic establishing shot.",
+    "A skateboarder doing a kickflip in an urban plaza, slow motion, golden hour lighting.",
+]
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    p.add_argument("--model", required=True, help="Input HV-1.5 diffusers directory or HF id.")
+    p.add_argument("--output", required=True, help="Output directory for the ModelOpt FP8 checkpoint.")
+    p.add_argument("--dtype", choices=("bfloat16", "float16"), default="bfloat16")
+    p.add_argument("--height", type=int, default=480)
+    p.add_argument("--width", type=int, default=832)
+    p.add_argument(
+        "--num-frames",
+        type=int,
+        default=33,
+        help="Frames per calibration sample. 33 matches the typical short benchmark.",
+    )
+    p.add_argument("--guidance-scale", type=float, default=6.0)
+    p.add_argument(
+        "--calib-steps",
+        type=int,
+        default=10,
+        help="Denoising steps per calibration prompt (10 is enough for amax statistics).",
+    )
+    p.add_argument("--calib-size", type=int, default=8, help="How many prompts to use for calibration.")
+    p.add_argument("--seed", type=int, default=42)
+    p.add_argument(
+        "--prompt",
+        action="append",
+        default=[],
+        help="Custom calibration prompt. Repeat to provide multiple.",
+    )
+    p.add_argument(
+        "--quantize-mha",
+        action="store_true",
+        help="Enable FP8 attention K/V/softmax quantizers. Off by default — empirically degrades HV-1.5 video output.",
+    )
+    p.add_argument(
+        "--weight-block-size",
+        type=str,
+        default=None,
+        help="Per-block weight quantization as 'M,N' (e.g. '128,128' for 128x128 tiles). "
+        "Default: per-tensor (one scale per linear). Block-wise typically gives tighter quality at "
+        "negligible memory cost. Static FP8 is exempt from upstream vLLM's online block-wise gate.",
+    )
+    p.add_argument("--overwrite", action="store_true", help="Replace an existing output directory.")
+    return p
+
+
+def _parse_block_size(spec: str | None) -> list[int] | None:
+    if spec is None:
+        return None
+    parts = [int(x) for x in spec.split(",") if x.strip()]
+    if len(parts) != 2:
+        raise SystemExit(f"--weight-block-size must be 'M,N' (2 ints), got {spec!r}")
+    return parts
+
+
+def _require_modelopt() -> Any:
+    try:
+        import modelopt.torch.quantization as mtq
+    except ModuleNotFoundError as exc:
+        raise SystemExit(
+            "NVIDIA ModelOpt is not installed. Install with:\n"
+            "  pip install 'nvidia-modelopt[all]'\n"
+            f"Original error: {exc}"
+        ) from exc
+    return mtq
+
+
+def _ensure_paths(args: argparse.Namespace) -> tuple[str, Path]:
+    model_path = args.model
+    output_dir = Path(args.output).expanduser().resolve()
+    if output_dir.exists():
+        if not args.overwrite:
+            raise SystemExit(f"Output directory already exists: {output_dir}\nPass --overwrite to replace it.")
+        shutil.rmtree(output_dir)
+    return model_path, output_dir
+
+
+def _select_dtype(name: str) -> torch.dtype:
+    return {"bfloat16": torch.bfloat16, "float16": torch.float16}[name]
+
+
+def _build_prompts(args: argparse.Namespace) -> list[str]:
+    prompts = args.prompt or DEFAULT_PROMPTS
+    if args.calib_size <= 0:
+        raise SystemExit("--calib-size must be positive.")
+    if len(prompts) < args.calib_size:
+        repeats = (args.calib_size + len(prompts) - 1) // len(prompts)
+        prompts = (prompts * repeats)[: args.calib_size]
+    return prompts[: args.calib_size]
+
+
+# Layers to KEEP at full precision (mirror of the #2920 wiring + #2728/#2795 skip pattern).
+# - x_embedder, image_embedder, context_embedder*, time_embed*, cond_type_embed: entry/embedding
+# - norm_out, norm1*.linear, norm1_context*.linear, norm2*, norm2_context*: AdaLayerNorm modulation
+# - proj_out: final output projection
+# - token_refiner*: text-encoder refinement uses diffusers raw nn.Linear
+def _filter_func_hv15(name: str) -> bool:
+    pattern = re.compile(
+        r"(proj_out.*|"
+        r".*(x_embedder|image_embedder|context_embedder|context_embedder_2|"
+        r"time_embed|cond_type_embed|"
+        r"norm_out|norm1\.linear|norm1_context\.linear|norm2|norm2_context|"
+        r"token_refiner).*)"
+    )
+    return pattern.match(name) is not None
+
+
+def _mha_filter_func(name: str) -> bool:
+    pattern = re.compile(
+        r".*(q_bmm_quantizer|k_bmm_quantizer|v_bmm_quantizer|softmax_quantizer|bmm2_output_quantizer).*"
+    )
+    return pattern.match(name) is not None
+
+
+def _disable_known_problematic_quantizers(mtq: Any, backbone: torch.nn.Module, *, quantize_mha: bool) -> None:
+    if not hasattr(mtq, "disable_quantizer"):
+        return
+    mtq.disable_quantizer(backbone, _filter_func_hv15)
+    if not quantize_mha:
+        mtq.disable_quantizer(backbone, _mha_filter_func)
+
+
+def _load_pipeline(model_path: str, dtype: torch.dtype) -> DiffusionPipeline:
+    pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=dtype)
+    if hasattr(pipe, "set_progress_bar_config"):
+        pipe.set_progress_bar_config(disable=True)
+    pipe.to("cuda")
+    return pipe
+
+
+def _build_forward_loop(pipe: DiffusionPipeline, args: argparse.Namespace, prompts: list[str]):
+    generator = torch.Generator(device="cuda")
+
+    # Try to set guidance on the pipeline's guider object up front (modern
+    # diffusers HV-1.5 uses a Guider abstraction, not a per-call kwarg). Falls
+    # back silently — calibration uses whatever default the pipeline ships with.
+    guider = getattr(pipe, "guider", None)
+    if guider is not None and hasattr(guider, "guidance_scale"):
+        try:
+            guider.guidance_scale = args.guidance_scale
+        except Exception:
+            pass
+
+    base_kwargs = dict(
+        height=args.height,
+        width=args.width,
+        num_frames=args.num_frames,
+        num_inference_steps=args.calib_steps,
+        output_type="latent",
+    )
+
+    def forward_loop(*_unused_args, **_unused_kwargs) -> None:
+        with torch.inference_mode():
+            for idx, prompt in enumerate(prompts):
+                generator.manual_seed(args.seed + idx)
+                # Try with guidance_scale first; fall back without on TypeError
+                # for pipelines (like HV-1.5) that take CFG via guider config.
+                try:
+                    pipe(prompt=prompt, generator=generator, guidance_scale=args.guidance_scale, **base_kwargs)
+                except TypeError as exc:
+                    if "guidance_scale" not in str(exc):
+                        raise
+                    pipe(prompt=prompt, generator=generator, **base_kwargs)
+
+    return forward_loop
+
+
+def _summarize_export(output_dir: Path) -> None:
+    cfg_path = output_dir / "transformer" / "config.json"
+    if not cfg_path.exists():
+        print(f"[warn] {cfg_path} missing.", file=sys.stderr)
+        return
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+    qc = cfg.get("quantization_config")
+    if not isinstance(qc, dict):
+        print("[warn] No quantization_config in transformer/config.json.", file=sys.stderr)
+        return
+    print("Export summary:")
+    print(f"  quant_method: {qc.get('quant_method')}")
+    print(f"  quant_algo:   {qc.get('quant_algo')}")
+    producer = qc.get("producer")
+    if isinstance(producer, dict):
+        print(f"  producer:     {producer.get('name')} {producer.get('version')}")
+    print(f"  config path:  {cfg_path}")
+
+
+def _force_export_quantized_weights(backbone: torch.nn.Module, dtype: torch.dtype) -> int:
+    """Convert in-memory weights of quantized modules to actual FP8 storage.
+
+    `export_hf_checkpoint` skips this step for unknown model types (HV-1.5 isn't
+    in ModelOpt's recognized-model registry), so we must call the per-weight
+    export helper ourselves. Same workaround as the HunyuanImage-3 calibration
+    helper.
+    """
+    from modelopt.torch.export.quant_utils import (
+        QUANTIZATION_NONE,
+        get_quantization_format,
+        quantizer_attr_names,
+        weight_attr_names,
+    )
+    from modelopt.torch.export.unified_export_hf import _export_quantized_weight
+
+    exported = 0
+    for name, module in backbone.named_modules():
+        try:
+            quantization_format = get_quantization_format(module)
+        except Exception as exc:
+            print(f"[warn] Could not inspect quantization format for {name}: {exc}", file=sys.stderr)
+            continue
+        if quantization_format == QUANTIZATION_NONE:
+            continue
+        for weight_name in weight_attr_names(module):
+            quantizer_attrs = quantizer_attr_names(weight_name)
+            weight_quantizer = getattr(module, quantizer_attrs.weight_quantizer, None)
+            if weight_quantizer is None or not getattr(weight_quantizer, "is_enabled", False):
+                continue
+            _export_quantized_weight(module, dtype, weight_name)
+            exported += 1
+    return exported
+
+
+def _hv15_quant_config_block(weight_block_size: list[int] | None = None) -> dict:
+    """Mirror ModelOpt FP8 metadata expected by vllm-omni's adapter (#2913).
+
+    Same shape as the HunyuanImage-3 author's _hunyuan_quant_config(). When
+    `weight_block_size` is given, advertise block-wise weight quantization in
+    the saved metadata (so consumers know to expect multi-element scale tensors).
+    """
+    weights_cfg: dict = {"dynamic": False, "num_bits": 8, "type": "float"}
+    if weight_block_size is not None:
+        weights_cfg["strategy"] = "block"
+        weights_cfg["block_structure"] = f"{weight_block_size[0]}x{weight_block_size[1]}"
+    return {
+        "config_groups": {
+            "group_0": {
+                "input_activations": {"dynamic": False, "num_bits": 8, "type": "float"},
+                "weights": weights_cfg,
+                "targets": ["Linear"],
+            }
+        },
+        "ignore": [
+            "context_embedder*",
+            "context_embedder_2*",
+            "cond_type_embed*",
+            "image_embedder*",
+            "norm1.linear*",
+            "norm1_context.linear*",
+            "norm2*",
+            "norm2_context*",
+            "norm_out*",
+            "proj_out*",
+            "time_embed*",
+            "token_refiner*",
+            "x_embedder*",
+        ],
+        "producer": {"name": "modelopt"},
+        "quant_algo": "FP8",
+        "quant_method": "modelopt",
+    }
+
+
+def _patch_quant_config(output_dir: Path, weight_block_size: list[int] | None = None) -> None:
+    """Inject quant_algo: FP8 + config_groups into transformer/config.json so
+    vllm-omni's adapter (#2913) recognises the checkpoint as ModelOpt FP8."""
+    cfg_path = output_dir / "transformer" / "config.json"
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+
+    new_qc = _hv15_quant_config_block(weight_block_size=weight_block_size)
+    existing = cfg.get("quantization_config")
+    if isinstance(existing, dict):
+        producer = existing.get("producer")
+        if isinstance(producer, dict):
+            new_qc["producer"] = producer
+
+    cfg["quantization_config"] = new_qc
+    with cfg_path.open("w", encoding="utf-8") as f:
+        json.dump(cfg, f, indent=2)
+
+
+def _save_pipeline_with_fp8_transformer(
+    pipe: DiffusionPipeline,
+    model_path: str,
+    output_dir: Path,
+    max_shard_size: str = "5GB",
+) -> None:
+    """Save the pipeline with the (now FP8) transformer.
+
+    Copies the source directory verbatim except for `transformer/`, then
+    saves the transformer with quantizers hidden so the state dict contains
+    only the FP8 weights + scale tensors.
+    """
+    from modelopt.torch.export.diffusers_utils import hide_quantizers_from_state_dict
+
+    src = Path(model_path)
+    if not src.exists():
+        from huggingface_hub import snapshot_download
+
+        src = Path(snapshot_download(model_path))
+
+    if output_dir.exists():
+        shutil.rmtree(output_dir)
+    shutil.copytree(src, output_dir, ignore=shutil.ignore_patterns("transformer"))
+
+    transformer_out = output_dir / "transformer"
+    # `hide_quantizers_from_state_dict` walks named_modules(); pass the actual
+    # nn.Module (transformer), not the diffusers Pipeline wrapper.
+    with hide_quantizers_from_state_dict(pipe.transformer):
+        pipe.transformer.save_pretrained(
+            str(transformer_out),
+            safe_serialization=True,
+            max_shard_size=max_shard_size,
+        )
+
+
+def main() -> None:
+    args = _build_parser().parse_args()
+    if not torch.cuda.is_available():
+        raise SystemExit("CUDA is required for ModelOpt FP8 quantization.")
+
+    mtq = _require_modelopt()
+    model_path, output_dir = _ensure_paths(args)
+    dtype = _select_dtype(args.dtype)
+    prompts = _build_prompts(args)
+
+    print("Quantization plan:")
+    weight_block_size = _parse_block_size(args.weight_block_size)
+
+    print(f"  input:           {args.model}")
+    print(f"  output:          {output_dir}")
+    print(f"  dtype:           {dtype}")
+    print(f"  height/width:    {args.height}x{args.width}")
+    print(f"  num_frames:      {args.num_frames}")
+    print(f"  calib_size:      {len(prompts)}")
+    print(f"  calib_steps:     {args.calib_steps}")
+    print(f"  quantize_mha:    {args.quantize_mha}")
+    print(
+        f"  weight strategy: {'block-wise ' + str(weight_block_size) if weight_block_size else 'per-tensor (default)'}"
+    )
+
+    pipe = _load_pipeline(model_path, dtype)
+    backbone = pipe.transformer
+
+    quant_config = copy.deepcopy(mtq.FP8_DEFAULT_CFG)
+    if weight_block_size is not None:
+        # Switch from per-tensor (default) to block-wise weight quantization.
+        # ModelOpt's wildcard "*weight_quantizer" matches every linear's weight quantizer.
+        quant_config["quant_cfg"]["*weight_quantizer"] = {
+            "num_bits": (4, 3),  # E4M3 (FP8 weights, same as default)
+            "block_sizes": {-1: weight_block_size[1], -2: weight_block_size[0]},
+        }
+        print(
+            f"  -> overriding weight quantizer with block_sizes={weight_block_size} "
+            f"({weight_block_size[0]}x{weight_block_size[1]} tiles)"
+        )
+
+    forward_loop = _build_forward_loop(pipe, args, prompts)
+    quantized = mtq.quantize(backbone, quant_config, forward_loop)
+    if quantized is not None:
+        pipe.transformer = quantized
+        backbone = quantized
+
+    _disable_known_problematic_quantizers(mtq, backbone, quantize_mha=args.quantize_mha)
+
+    print("\nForcing FP8 weight serialization (HV-1.5 isn't in ModelOpt's recognized-model registry,")
+    print("so we have to call the per-weight export helper ourselves)...")
+    exported = _force_export_quantized_weights(backbone, dtype)
+    print(f"  -> {exported} weights converted to FP8 in memory")
+    if exported == 0:
+        raise SystemExit(
+            "No quantized weights were exported. Calibration may have skipped every layer "
+            "(check the disable_quantizer regex) or `mtq.quantize` did not actually wrap any "
+            "weight quantizers."
+        )
+
+    print("\nSaving pipeline with FP8 transformer...")
+    _save_pipeline_with_fp8_transformer(pipe, model_path, output_dir)
+    _patch_quant_config(output_dir, weight_block_size=weight_block_size)
+    print(f"Saved to: {output_dir}")
+    _summarize_export(output_dir)
+
+    print("\nNext: validate the checkpoint with vllm-omni:")
+    print(
+        "  python examples/offline_inference/text_to_video/text_to_video.py \\\n"
+        f"    --model {output_dir} \\\n"
+        "    --quantization fp8 \\\n"
+        "    --prompt 'A dog running across a field of golden wheat.' \\\n"
+        f"    --height {args.height} --width {args.width} --num-frames {args.num_frames} \\\n"
+        "    --num-inference-steps 30 --guidance-scale 6.0 --seed 42 \\\n"
+        "    --output outputs/hv15_modelopt_fp8.mp4 \\\n"
+        "    --enforce-eager"
+    )
+    print(
+        "\n  (--quantization fp8 is auto-upgraded to ModelOpt FP8 at runtime because the "
+        "checkpoint's config.json has modelopt metadata.)"
+    )
+
+
+if __name__ == "__main__":
+    main()

examples/quantization/quantize_wan2_2_modelopt_fp8.py

@@ -0,0 +1,471 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Quantize Wan2.2 (TI2V-5B, 704x1280 T2V) to a ModelOpt FP8 Hugging Face checkpoint.
+
+Calibrates the DiT transformer using a small video prompt set and exports a
+diffusers-style directory whose transformer carries ModelOpt FP8 metadata.
+The exported checkpoint is consumable by vllm-omni's ModelOpt FP8 adapter
+(see vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py).
+
+Layers kept full precision match the #2728 / #2795 pattern: condition embedder
+(time/text/image), patch embedding, modulation (scale_shift_table), final
+norm + proj_out, and sequence-parallel helpers. All attention + FFN linears
+are quantized — static calibration handles the numerics that online FP8
+couldn't (see #2920 ablation).
+
+Default target is `Wan-AI/Wan2.2-TI2V-5B-Diffusers`, the dense 5B variant that
+fits 80GB BF16. The A14B MoE variants need 2+ GPUs and are out of scope here.
+
+Example:
+    python examples/quantization/quantize_wan2_2_modelopt_fp8.py \\
+        --model Wan-AI/Wan2.2-TI2V-5B-Diffusers \\
+        --output ./wan22-ti2v-modelopt-fp8 \\
+        --overwrite
+"""
+
+from __future__ import annotations
+
+import argparse
+import copy
+import json
+import re
+import shutil
+import sys
+from pathlib import Path
+from typing import Any
+
+import torch
+from diffusers import DiffusionPipeline
+
+DEFAULT_PROMPTS = [
+    "A dog running across a field of golden wheat.",
+    "An astronaut riding a horse across the surface of Mars, red dust swirling, cinematic wide shot.",
+    "A hummingbird hovering in front of a vibrant red flower, slow motion, macro shot.",
+    "A crackling campfire at night under a starry sky, sparks rising into the dark.",
+    "An underwater shot of a coral reef with tropical fish swimming by, sun rays piercing the water.",
+    "A close-up of a blooming rose covered in morning dew, soft natural light.",
+    "A peaceful mountain village at dawn, mist rolling over the rooftops, cinematic establishing shot.",
+    "A skateboarder doing a kickflip in an urban plaza, slow motion, golden hour lighting.",
+]
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    p.add_argument("--model", required=True, help="Input Wan2.2 diffusers directory or HF id.")
+    p.add_argument("--output", required=True, help="Output directory for the ModelOpt FP8 checkpoint.")
+    p.add_argument("--dtype", choices=("bfloat16", "float16"), default="bfloat16")
+    p.add_argument("--height", type=int, default=704, help="Calibration video height (Wan2.2 TI2V-5B native: 704).")
+    p.add_argument("--width", type=int, default=1280, help="Calibration video width (Wan2.2 TI2V-5B native: 1280).")
+    p.add_argument(
+        "--num-frames",
+        type=int,
+        default=49,
+        help="Frames per calibration sample. 49 matches the typical short benchmark; "
+        "use 17 to reduce memory pressure during calibration.",
+    )
+    p.add_argument("--guidance-scale", type=float, default=5.0)
+    p.add_argument(
+        "--calib-steps",
+        type=int,
+        default=10,
+        help="Denoising steps per calibration prompt (10 is enough for amax statistics).",
+    )
+    p.add_argument("--calib-size", type=int, default=8, help="How many prompts to use for calibration.")
+    p.add_argument("--seed", type=int, default=42)
+    p.add_argument(
+        "--prompt",
+        action="append",
+        default=[],
+        help="Custom calibration prompt. Repeat to provide multiple.",
+    )
+    p.add_argument(
+        "--quantize-mha",
+        action="store_true",
+        help="Enable FP8 attention K/V/softmax quantizers. Off by default — Wan2.2's long attention "
+        "sequences amplified FP8 drift in the online ablation (see #2920).",
+    )
+    p.add_argument(
+        "--weight-block-size",
+        type=str,
+        default=None,
+        help="Per-block weight quantization as 'M,N' (e.g. '128,128'). Default per-tensor. "
+        "Note: vllm-omni's ModelOpt adapter may not yet dispatch block-wise scales — check #2924 "
+        "for the HV-1.5 investigation status before relying on this.",
+    )
+    p.add_argument("--overwrite", action="store_true", help="Replace an existing output directory.")
+    return p
+
+
+def _parse_block_size(spec: str | None) -> list[int] | None:
+    if spec is None:
+        return None
+    parts = [int(x) for x in spec.split(",") if x.strip()]
+    if len(parts) != 2:
+        raise SystemExit(f"--weight-block-size must be 'M,N' (2 ints), got {spec!r}")
+    return parts
+
+
+def _require_modelopt() -> Any:
+    try:
+        import modelopt.torch.quantization as mtq
+    except ModuleNotFoundError as exc:
+        raise SystemExit(
+            "NVIDIA ModelOpt is not installed. Install with:\n"
+            "  pip install 'nvidia-modelopt[all]'\n"
+            f"Original error: {exc}"
+        ) from exc
+    return mtq
+
+
+def _ensure_paths(args: argparse.Namespace) -> tuple[str, Path]:
+    model_path = args.model
+    output_dir = Path(args.output).expanduser().resolve()
+    if output_dir.exists():
+        if not args.overwrite:
+            raise SystemExit(f"Output directory already exists: {output_dir}\nPass --overwrite to replace it.")
+        shutil.rmtree(output_dir)
+    return model_path, output_dir
+
+
+def _select_dtype(name: str) -> torch.dtype:
+    return {"bfloat16": torch.bfloat16, "float16": torch.float16}[name]
+
+
+def _build_prompts(args: argparse.Namespace) -> list[str]:
+    prompts = args.prompt or DEFAULT_PROMPTS
+    if args.calib_size <= 0:
+        raise SystemExit("--calib-size must be positive.")
+    if len(prompts) < args.calib_size:
+        repeats = (args.calib_size + len(prompts) - 1) // len(prompts)
+        prompts = (prompts * repeats)[: args.calib_size]
+    return prompts[: args.calib_size]
+
+
+# Layers to KEEP at full precision. Wan2.2's module naming:
+# - condition_embedder: time_embedder, time_proj, text_embedder, image_embedder (I2V)
+# - patch_embedding: Conv3dLayer (already not Linear, belt-and-suspenders skip)
+# - scale_shift_table: nn.Parameter modulation (not Linear, but pattern guard)
+# - norm_out: AdaLayerNorm final
+# - proj_out: final nn.Linear
+# - timestep_proj_prepare / output_scale_shift_prepare: SP helpers
+def _filter_func_wan22(name: str) -> bool:
+    pattern = re.compile(
+        r"(proj_out.*|"
+        r".*(condition_embedder|patch_embedding|"
+        r"norm_out|scale_shift_table|"
+        r"timestep_proj_prepare|output_scale_shift_prepare).*)"
+    )
+    return pattern.match(name) is not None
+
+
+def _mha_filter_func(name: str) -> bool:
+    pattern = re.compile(
+        r".*(q_bmm_quantizer|k_bmm_quantizer|v_bmm_quantizer|softmax_quantizer|bmm2_output_quantizer).*"
+    )
+    return pattern.match(name) is not None
+
+
+def _disable_known_problematic_quantizers(mtq: Any, backbone: torch.nn.Module, *, quantize_mha: bool) -> None:
+    if not hasattr(mtq, "disable_quantizer"):
+        return
+    mtq.disable_quantizer(backbone, _filter_func_wan22)
+    if not quantize_mha:
+        mtq.disable_quantizer(backbone, _mha_filter_func)
+
+
+def _load_pipeline(model_path: str, dtype: torch.dtype) -> DiffusionPipeline:
+    pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=dtype)
+    if hasattr(pipe, "set_progress_bar_config"):
+        pipe.set_progress_bar_config(disable=True)
+    pipe.to("cuda")
+    return pipe
+
+
+def _build_forward_loop(pipe: DiffusionPipeline, args: argparse.Namespace, prompts: list[str]):
+    generator = torch.Generator(device="cuda")
+
+    # Try setting guidance on the pipeline's guider if present (newer diffusers APIs).
+    guider = getattr(pipe, "guider", None)
+    if guider is not None and hasattr(guider, "guidance_scale"):
+        try:
+            guider.guidance_scale = args.guidance_scale
+        except Exception:
+            pass
+
+    base_kwargs = dict(
+        height=args.height,
+        width=args.width,
+        num_frames=args.num_frames,
+        num_inference_steps=args.calib_steps,
+        output_type="latent",
+    )
+
+    def forward_loop(*_unused_args, **_unused_kwargs) -> None:
+        with torch.inference_mode():
+            for idx, prompt in enumerate(prompts):
+                generator.manual_seed(args.seed + idx)
+                # Try with guidance_scale first; fall back without on TypeError
+                # for pipelines that take CFG via guider config only.
+                try:
+                    pipe(prompt=prompt, generator=generator, guidance_scale=args.guidance_scale, **base_kwargs)
+                except TypeError as exc:
+                    if "guidance_scale" not in str(exc):
+                        raise
+                    pipe(prompt=prompt, generator=generator, **base_kwargs)
+
+    return forward_loop
+
+
+def _summarize_export(output_dir: Path) -> None:
+    cfg_path = output_dir / "transformer" / "config.json"
+    if not cfg_path.exists():
+        print(f"[warn] {cfg_path} missing.", file=sys.stderr)
+        return
+    with cfg_path.open(encoding="utf-8") as f:
+        cfg = json.load(f)
+    qc = cfg.get("quantization_config")
+    if not isinstance(qc, dict):
+        print("[warn] No quantization_config in transformer/config.json.", file=sys.stderr)
+        return
+    print("Export summary:")
+    print(f"  quant_method: {qc.get('quant_method')}")
+    print(f"  quant_algo:   {qc.get('quant_algo')}")
+    producer = qc.get("producer")
+    if isinstance(producer, dict):
+        print(f"  producer:     {producer.get('name')} {producer.get('version')}")
+    print(f"  config path:  {cfg_path}")
+
+
+def _force_export_quantized_weights(backbone: torch.nn.Module, dtype: torch.dtype) -> int:
+    """Convert in-memory weights of quantized modules to actual FP8 storage.
+
+    `export_hf_checkpoint` skips this step for unknown model types (Wan2.2 isn't
+    in ModelOpt's recognized-model registry), so we must call the per-weight
+    export helper ourselves. Same workaround as the HunyuanVideo-1.5 / HunyuanImage-3
+    calibration helpers.
+    """
+    from modelopt.torch.export.quant_utils import (
+        QUANTIZATION_NONE,
+        get_quantization_format,
+        quantizer_attr_names,
+        weight_attr_names,
+    )
+    from modelopt.torch.export.unified_export_hf import _export_quantized_weight
+
+    exported = 0
+    for name, module in backbone.named_modules():
+        try:
+            quantization_format = get_quantization_format(module)
+        except Exception as exc:
+            print(f"[warn] Could not inspect quantization format for {name}: {exc}", file=sys.stderr)
+            continue
+        if quantization_format == QUANTIZATION_NONE:
+            continue
+        for weight_name in weight_attr_names(module):
+            quantizer_attrs = quantizer_attr_names(weight_name)
+            weight_quantizer = getattr(module, quantizer_attrs.weight_quantizer, None)
+            if weight_quantizer is None or not getattr(weight_quantizer, "is_enabled", False):
+                continue
+            _export_quantized_weight(module, dtype, weight_name)
+            exported += 1
+    return exported
+
+
+def _wan22_quant_config_block(weight_block_size: list[int] | None = None) -> dict:
+    """Mirror ModelOpt FP8 metadata expected by vllm-omni's adapter (#2913)."""
+    weights_cfg: dict = {"dynamic": False, "num_bits": 8, "type": "float"}
+    if weight_block_size is not None:
+        weights_cfg["strategy"] = "block"
+        weights_cfg["block_structure"] = f"{weight_block_size[0]}x{weight_block_size[1]}"
+    return {
+        "config_groups": {
+            "group_0": {
+                "input_activations": {"dynamic": False, "num_bits": 8, "type": "float"},
+                "weights": weights_cfg,
+                "targets": ["Linear"],
+            }
+        },
+        "ignore": [
+            "condition_embedder*",
+            "norm_out*",
+            "output_scale_shift_prepare*",
+            "patch_embedding*",
+            "proj_out*",
+            "scale_shift_table*",
+            "timestep_proj_prepare*",
+        ],
+        "producer": {"name": "modelopt"},
+        "quant_algo": "FP8",
+        "quant_method": "modelopt",
+    }
+
+
+def _patch_quant_config(output_dir: Path, weight_block_size: list[int] | None = None) -> None:
+    """Inject quant_algo: FP8 + config_groups into each transformer's config.json
+    so vllm-omni's adapter (#2913) recognises the checkpoint as ModelOpt FP8.
+
+    Patches both ``transformer`` and ``transformer_2`` (A14B) when present."""
+    for sub in ("transformer", "transformer_2"):
+        cfg_path = output_dir / sub / "config.json"
+        if not cfg_path.exists():
+            continue
+        with cfg_path.open(encoding="utf-8") as f:
+            cfg = json.load(f)
+
+        new_qc = _wan22_quant_config_block(weight_block_size=weight_block_size)
+        existing = cfg.get("quantization_config")
+        if isinstance(existing, dict):
+            producer = existing.get("producer")
+            if isinstance(producer, dict):
+                new_qc["producer"] = producer
+
+        cfg["quantization_config"] = new_qc
+        with cfg_path.open("w", encoding="utf-8") as f:
+            json.dump(cfg, f, indent=2)
+
+
+def _list_transformers(pipe: DiffusionPipeline) -> list[tuple[str, torch.nn.Module]]:
+    """Return [(attr_name, module)] for every DiT on the pipeline.
+
+    Wan2.2 A14B has both ``transformer`` (low-noise) and ``transformer_2``
+    (high-noise). TI2V-5B has only ``transformer``.
+    """
+    out = []
+    for attr in ("transformer", "transformer_2"):
+        mod = getattr(pipe, attr, None)
+        if mod is not None:
+            out.append((attr, mod))
+    return out
+
+
+def _save_pipeline_with_fp8_transformer(
+    pipe: DiffusionPipeline,
+    model_path: str,
+    output_dir: Path,
+    max_shard_size: str = "5GB",
+) -> None:
+    """Copy source dir verbatim minus transformer dirs, then save each quantized DiT.
+
+    Handles A14B's dual transformer (``transformer`` + ``transformer_2``) as well
+    as the single-DiT TI2V-5B.
+    """
+    from modelopt.torch.export.diffusers_utils import hide_quantizers_from_state_dict
+
+    src = Path(model_path)
+    if not src.exists():
+        from huggingface_hub import snapshot_download
+
+        src = Path(snapshot_download(model_path))
+
+    if output_dir.exists():
+        shutil.rmtree(output_dir)
+    shutil.copytree(src, output_dir, ignore=shutil.ignore_patterns("transformer", "transformer_2"))
+
+    for attr, backbone in _list_transformers(pipe):
+        transformer_out = output_dir / attr
+        # Pass the nn.Module (transformer), not the Pipeline wrapper.
+        with hide_quantizers_from_state_dict(backbone):
+            backbone.save_pretrained(
+                str(transformer_out),
+                safe_serialization=True,
+                max_shard_size=max_shard_size,
+            )
+
+
+def main() -> None:
+    args = _build_parser().parse_args()
+    if not torch.cuda.is_available():
+        raise SystemExit("CUDA is required for ModelOpt FP8 quantization.")
+
+    mtq = _require_modelopt()
+    model_path, output_dir = _ensure_paths(args)
+    dtype = _select_dtype(args.dtype)
+    prompts = _build_prompts(args)
+    weight_block_size = _parse_block_size(args.weight_block_size)
+
+    print("Quantization plan:")
+    print(f"  input:           {args.model}")
+    print(f"  output:          {output_dir}")
+    print(f"  dtype:           {dtype}")
+    print(f"  height/width:    {args.height}x{args.width}")
+    print(f"  num_frames:      {args.num_frames}")
+    print(f"  calib_size:      {len(prompts)}")
+    print(f"  calib_steps:     {args.calib_steps}")
+    print(f"  quantize_mha:    {args.quantize_mha}")
+    print(
+        f"  weight strategy: {'block-wise ' + str(weight_block_size) if weight_block_size else 'per-tensor (default)'}"
+    )
+
+    pipe = _load_pipeline(model_path, dtype)
+    transformers = _list_transformers(pipe)
+    if not transformers:
+        raise SystemExit("Pipeline has no transformer or transformer_2 attribute.")
+    print(f"  found {len(transformers)} transformer(s): {', '.join(a for a, _ in transformers)}")
+
+    quant_config = copy.deepcopy(mtq.FP8_DEFAULT_CFG)
+    if weight_block_size is not None:
+        quant_config["quant_cfg"]["*weight_quantizer"] = {
+            "num_bits": (4, 3),
+            "block_sizes": {-1: weight_block_size[1], -2: weight_block_size[0]},
+        }
+        print(
+            f"  -> overriding weight quantizer with block_sizes={weight_block_size} "
+            f"({weight_block_size[0]}x{weight_block_size[1]} tiles)"
+        )
+
+    forward_loop = _build_forward_loop(pipe, args, prompts)
+
+    # Quantize each DiT. The forward_loop runs the full pipeline, so quantizers
+    # on every attached transformer (A14B: transformer + transformer_2) get
+    # calibrated during the same passes.
+    for attr, backbone in transformers:
+        print(f"\nQuantizing {attr}...")
+        quantized = mtq.quantize(backbone, quant_config, forward_loop)
+        if quantized is not None:
+            setattr(pipe, attr, quantized)
+        _disable_known_problematic_quantizers(mtq, getattr(pipe, attr), quantize_mha=args.quantize_mha)
+
+    # Export weights to FP8 only AFTER all transformers are calibrated. Exporting
+    # inside the loop would convert transformer's weights to real FP8, and the
+    # next transformer's forward_loop (full pipeline) would then fake-quantize an
+    # already-FP8 weight -> "fake_e4m3fy not implemented for Float8_e4m3fn".
+    print("\nForcing FP8 weight serialization (Wan2.2 isn't in ModelOpt's recognized-model registry,")
+    print("so we have to call the per-weight export helper ourselves)...")
+    total_exported = 0
+    for attr, backbone in _list_transformers(pipe):
+        exported = _force_export_quantized_weights(backbone, dtype)
+        print(f"  -> {exported} weights converted to FP8 in {attr}")
+        total_exported += exported
+
+    if total_exported == 0:
+        raise SystemExit(
+            "No quantized weights were exported. Calibration may have skipped every layer "
+            "(check the disable_quantizer regex) or `mtq.quantize` did not actually wrap any "
+            "weight quantizers."
+        )
+
+    print("\nSaving pipeline with FP8 transformer(s)...")
+    _save_pipeline_with_fp8_transformer(pipe, model_path, output_dir)
+    _patch_quant_config(output_dir, weight_block_size=weight_block_size)
+    print(f"Saved to: {output_dir}")
+    _summarize_export(output_dir)
+
+    print("\nNext: validate the checkpoint with vllm-omni:")
+    print(
+        "  python examples/offline_inference/text_to_video/text_to_video.py \\\n"
+        f"    --model {output_dir} \\\n"
+        "    --quantization fp8 \\\n"
+        "    --prompt 'A dog running across a field of golden wheat.' \\\n"
+        f"    --height {args.height} --width {args.width} --num-frames {args.num_frames} \\\n"
+        "    --num-inference-steps 30 --guidance-scale 5.0 --seed 42 \\\n"
+        "    --output outputs/wan22_modelopt_fp8.mp4"
+    )
+    print(
+        "\n  (--quantization fp8 is auto-upgraded to ModelOpt FP8 at runtime because the "
+        "checkpoint's config.json has modelopt metadata.)"
+    )
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -84,26 +84,11 @@ forced-aligner = [
     "qwen-asr>=0.0.6",  # faithful Japanese/Korean word segmentation for the TTS forced aligner
 ]
 
-indextts2 = [
-    "fugashi>=1.2.0",
-    "unidic-lite>=1.0.0",
-    "wetext>=0.0.9; sys_platform != 'linux'",
-    "WeTextProcessing; sys_platform == 'linux'",
-]
-
 # Local-test-only extras
 local = [
     "FlagEmbedding",
 ]
 
-# LongCat-Video-Avatar A2V/AI2V runtime dependencies for vocal
-# separation and loudness normalization.
-longcat-video-avatar = [
-    "audio-separator==0.44.2",
-    "pyloudnorm==0.1.1",
-    "soundfile>=0.13.1",
-]
-
 # Optional Blackwell-only fused-bias FP8 GEMM; package is `quack-kernels` (imported
 # as `quack`), not the unrelated `quack`. See docs/user_guide/quantization/fp8.md.
 quack = [
@@ -334,7 +319,3 @@ byt5 = "byt5"
 # "seeked" is the standard HTML media element DOM event name (fires when a
 # seek completes), used by the word-timestamps Gradio demo. Not a typo.
 seeked = "seeked"
-# IndexTTS 2.5 language codes and speech-emotion-recognition event token.
-fo = "fo"
-ba = "ba"
-SER = "SER"

recipes/IndexTeam/IndexTTS-2_5.md

@@ -1,308 +0,0 @@
-# IndexTTS-2.5 for multilingual voice-cloned TTS on 1x GPU
-
-## Summary
-
-- Vendor: IndexTeam
-- Model: `IndexTeam/IndexTTS-2.5`
-- Task: Multilingual text-to-speech with voice cloning, emotion control, and
-  native speed control
-- Mode: Online serving with the OpenAI-compatible `/v1/audio/speech` API, or
-  offline inference through `Omni`
-- Maintainer: Community
-
-## When to use this recipe
-
-Use this recipe to serve IndexTTS-2.5 as a two-stage TTS system. Stage 0 is an
-autoregressive talker; Stage 1 uses EnhancedCodec, S2Mel CFM/DiT, and BigVGAN
-to produce 22.05 kHz mono speech. Each request supplies synthesis text and
-reference audio, or an uploaded audio voice, for zero-shot voice cloning.
-
-IndexTTS-2.5 adds multilingual text processing and model-native speed control
-to the IndexTTS-2 serving contract.
-
-## References
-
-- Upstream model:
-  [IndexTeam/IndexTTS-2.5 on Hugging Face](https://huggingface.co/IndexTeam/IndexTTS-2.5)
-- Online serving example:
-  [`examples/online_serving/text_to_speech/README.md#indextts-2-and-indextts-25`](../../examples/online_serving/text_to_speech/README.md#indextts-2-and-indextts-25)
-- Offline inference example:
-  [`examples/offline_inference/text_to_speech/README.md#indextts-2-and-indextts-25`](../../examples/offline_inference/text_to_speech/README.md#indextts-2-and-indextts-25)
-- OpenAI-compatible client:
-  [`examples/online_serving/text_to_speech/indextts2/speech_client.py`](../../examples/online_serving/text_to_speech/indextts2/speech_client.py)
-- Standard deploy config:
-  [`vllm_omni/deploy/indextts2_5.yaml`](../../vllm_omni/deploy/indextts2_5.yaml)
-
-## Hardware Support
-
-### GPU
-
-### 1x NVIDIA H20 96GB
-
-#### Environment
-
-- OS: Linux
-- Python: 3.10+
-- Driver / runtime: NVIDIA CUDA environment
-- vLLM version: Match the repository requirements for your checkout
-- vLLM-Omni version or commit: Use the commit you are deploying from
-
-Install vLLM-Omni with the IndexTTS text-processing dependencies:
-
-```bash
-pip install 'vllm-omni[indextts2]'
-```
-
-Obtain the native IndexTTS-2.5 bundle and point `MODEL` at its root. The model
-loader accepts the upstream nested `checkpoints/` layout.
-
-#### Command
-
-Start the standard code-only server from the repository root:
-
-```bash
-MODEL_VERSION=2.5 \
-MODEL=/path/to/indextts-2.5 \
-bash examples/online_serving/text_to_speech/indextts2/run_server.sh
-```
-
-This selects `vllm_omni/deploy/indextts2_5.yaml`, which uses
-`use_gpt_latent=false`. To launch directly:
-
-```bash
-vllm serve /path/to/indextts-2.5 \
-  --omni \
-  --trust-remote-code \
-  --port 8092 \
-  --deploy-config vllm_omni/deploy/indextts2_5.yaml
-```
-
-#### Optional: NVIDIA MPS for higher single-GPU throughput
-
-Stage 0 and Stage 1 run in separate processes on the same GPU. Enabling
-NVIDIA Multi-Process Service (MPS) can improve steady-state throughput by
-allowing work from both stages to overlap more effectively. MPS is an opt-in
-deployment optimization: this recipe does not start it automatically, and the
-gain depends on the request mix and concurrency, so benchmark it with the
-intended workload before enabling it in production.
-
-Pay attention to CUDA device renumbering. For example, if the MPS control
-daemon is started with physical `CUDA_VISIBLE_DEVICES=1`, that GPU is exposed
-to MPS clients as logical device `0`; launch the server with
-`CUDA_VISIBLE_DEVICES=0`, not `1`. Use a dedicated MPS pipe/log directory when
-the host is shared with other services, and stop only the MPS daemon owned by
-this deployment.
-
-#### Verification
-
-Send a multilingual voice-cloning request with the bundled client. Local audio
-paths are converted to base64 data URLs before transmission:
-
-```bash
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --api-base http://localhost:8092 \
-  --model-version 2.5 \
-  --model /path/to/indextts-2.5 \
-  --lang zh \
-  --text "你好，这是 IndexTTS-2.5 语音合成测试。" \
-  --ref-audio /path/to/reference.wav \
-  --output indextts2_5.wav
-```
-
-##### Native speed control
-
-The public `speed` field is handled natively. Its accepted range is
-`[0.5, 2.0]`; values above `1.0` produce shorter, faster speech. The serving
-adapter converts the API convention to the model-native control with
-`duration_factor = 1.0 / speed`, so `speed=1.25` uses
-`duration_factor=0.8`:
-
-```bash
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --api-base http://localhost:8092 \
-  --model-version 2.5 \
-  --model /path/to/indextts-2.5 \
-  --speed 1.25 \
-  --text "这是使用模型原生语速控制的测试。" \
-  --ref-audio /path/to/reference.wav \
-  --output indextts2_5_speed.wav
-```
-
-##### Upload and reuse a named voice
-
-Upload a reference recording once when callers should reuse the same voice
-without sending `ref_audio` on every request. `consent` is required by the
-voice-storage API:
-
-```bash
-curl -X POST http://localhost:8092/v1/audio/voices \
-  -F "audio_sample=@/path/to/reference.wav" \
-  -F "consent=user-consent-id" \
-  -F "name=indextts_demo_voice" \
-  -F "speaker_description=IndexTTS-2.5 demonstration voice"
-```
-
-Confirm that the voice was stored, then synthesize with its name instead of a
-reference-audio payload:
-
-```bash
-curl http://localhost:8092/v1/audio/voices
-
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --api-base http://localhost:8092 \
-  --model-version 2.5 \
-  --model /path/to/indextts-2.5 \
-  --voice indextts_demo_voice \
-  --lang zh \
-  --text "你好，这是复用已上传音色的语音合成测试。" \
-  --output indextts2_5_named_voice.wav
-```
-
-There are no built-in text-only preset voices. Each named IndexTTS voice must
-first be created from an uploaded reference recording.
-
-##### Multilingual synthesis and text normalization
-
-The client accepts `zh` (Mandarin), `en` (English), `zhen` (mixed Chinese and
-English), `ja` (Japanese), and `yue` (Cantonese). The following commands use
-the same reference voice across all supported language modes:
-
-```bash
-CLIENT=examples/online_serving/text_to_speech/indextts2/speech_client.py
-MODEL=/path/to/indextts-2.5
-REF_AUDIO=/path/to/reference.wav
-
-python "$CLIENT" --model-version 2.5 --model "$MODEL" \
-  --ref-audio "$REF_AUDIO" --lang zh \
-  --text "你好，这是中文语音合成测试。" --output indextts2_5_zh.wav
-
-python "$CLIENT" --model-version 2.5 --model "$MODEL" \
-  --ref-audio "$REF_AUDIO" --lang en \
-  --text "Hello, this is an English speech synthesis test." \
-  --output indextts2_5_en.wav
-
-python "$CLIENT" --model-version 2.5 --model "$MODEL" \
-  --ref-audio "$REF_AUDIO" --lang zhen \
-  --text "Hello，欢迎使用 IndexTTS 二点五。" --output indextts2_5_zhen.wav
-
-python "$CLIENT" --model-version 2.5 --model "$MODEL" \
-  --ref-audio "$REF_AUDIO" --lang ja \
-  --text "こんにちは、これは日本語の音声合成テストです。" \
-  --output indextts2_5_ja.wav
-
-python "$CLIENT" --model-version 2.5 --model "$MODEL" \
-  --ref-audio "$REF_AUDIO" --lang yue \
-  --text "你好，呢段係粵語語音合成測試。" --output indextts2_5_yue.wav
-```
-
-Text normalization is enabled by default. Disable it only when the input is
-already written exactly as it should be spoken:
-
-```bash
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --model-version 2.5 --model /path/to/indextts-2.5 \
-  --ref-audio /path/to/reference.wav --lang en --no-text-normalization \
-  --text "The temperature is twenty five degrees." \
-  --output indextts2_5_pre_normalized.wav
-```
-
-For raw HTTP requests, put the same language and text-normalization controls
-under `extra_params`:
-
-```bash
-curl http://localhost:8092/v1/audio/speech \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "/path/to/indextts-2.5",
-    "input": "This is an IndexTTS-2.5 test.",
-    "response_format": "wav",
-    "speed": 1.0,
-    "ref_audio": "data:audio/wav;base64,<BASE64_ENCODED_AUDIO>",
-    "extra_params": {
-      "lang": "en",
-      "text_normalization": true
-    }
-  }' \
-  --output indextts2_5_en.wav
-```
-
-##### Emotion control
-
-IndexTTS-2.5 supports an explicit eight-value emotion vector, an emotion text
-description, or a separate emotion-reference recording. Use one source at a
-time. Vector values are ordered as `happy`, `angry`, `sad`, `afraid`,
-`disgusted`, `melancholic`, `surprised`, and `calm`; each value must be in
-`[0, 1.2]`. `emo_alpha` controls the strength in `[0, 1]`.
-
-Use an explicit emotion vector for deterministic control:
-
-```bash
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --model-version 2.5 --model /path/to/indextts-2.5 \
-  --ref-audio /path/to/reference.wav --lang zh \
-  --text "今天真是令人开心的一天！" \
-  --emo-vector 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \
-  --emo-alpha 0.8 --output indextts2_5_happy_vector.wav
-```
-
-Infer the emotion from a natural-language description with `use_emo_text`:
-
-```bash
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --model-version 2.5 --model /path/to/indextts-2.5 \
-  --ref-audio /path/to/reference.wav --lang zh \
-  --text "我们终于完成了这项工作！" \
-  --use-emo-text --emo-text "开心、兴奋而且充满活力" \
-  --emo-alpha 0.8 --output indextts2_5_happy_text.wav
-```
-
-Transfer emotion from a recording while retaining the speaker identity from
-`ref_audio`:
-
-```bash
-python examples/online_serving/text_to_speech/indextts2/speech_client.py \
-  --model-version 2.5 --model /path/to/indextts-2.5 \
-  --ref-audio /path/to/reference.wav --lang zh \
-  --text "请用情绪参考音频中的表达方式朗读这句话。" \
-  --emo-audio /path/to/emotion_reference.wav \
-  --emo-alpha 0.8 --output indextts2_5_emotion_audio.wav
-```
-
-If multiple emotion sources are supplied, the official precedence is
-`use_emo_text` > `emo_vector` > `emo_audio` > the emotion in the speaker
-reference. `--use-random` is also available for exploratory random emotion
-prototypes, but should not be used when reproducible conditioning is required.
-
-For offline inference:
-
-```bash
-python examples/offline_inference/text_to_speech/indextts2/end2end.py \
-  --model /path/to/indextts-2.5 \
-  --model-version 2.5 \
-  --lang zh \
-  --speed 1.0 \
-  --text "你好，这是离线语音合成测试。" \
-  --ref-audio /path/to/reference.wav
-```
-
-#### Notes
-
-- Hardware scope: the standard recipe has been exercised on one NVIDIA H200.
-  It does not claim an unverified throughput or quality result.
-- Audio output: 22.05 kHz mono WAV.
-- Voice cloning: reference audio is required on the documented raw request
-  path. Alternatively, `voice` may name an uploaded audio voice; there is no
-  built-in text-only preset voice.
-- Native speed: serving maps `speed` to the model's duration factor and skips
-  generic waveform speed adjustment, so speed is applied exactly once.
-- Languages: common codes include `zh`, `en`, `zhen` (mixed Chinese/English),
-  `ja`, and `yue`; `Mandarin` is accepted as an alias for `zh`.
-- Japanese normalization: `ja` tokenization does not automatically expand
-  numbers, dates, or percentages. Write these inputs as readable Japanese text
-  before inference.
-- Emotion controls: `use_emo_text`, `emo_vector`, and `emo_audio` are
-  alternative conditioning modes. Their precedence is `use_emo_text` >
-  `emo_vector` > `emo_audio` > the speaker-reference emotion.
-- Sampling difference: Stage 0 uses plain vLLM sampling, not the upstream
-  default `num_beams=3` beam search. Use upstream `num_beams=1` for parity
-  comparisons; output may differ from the official beam-search result.

recipes/MiniMaxAI/MiniMax-H3-4090.md

@@ -1,169 +0,0 @@
-# MiniMax-H3 on RTX 4090
-
-This recipe uses BF16 weights, tiled VAE decode, tensor parallelism, optional
-Ulysses sequence parallelism, and distributed layerwise offload (DLO). It is the
-24 GiB sibling of [MiniMax-H3-5090.md](MiniMax-H3-5090.md): the two-GPU topology
-matches that recipe, but the resident DiT-block count is lower so the per-rank
-peak fits in 24 GiB. Lower resident counts reduce HBM use and increase
-CPU-to-GPU transfer time.
-
-## Capacity requirements
-
-| Resource | Two RTX 4090s | Four RTX 4090s |
-| --- | ---: | ---: |
-| GPU HBM | 24 GiB per GPU | 24 GiB per GPU |
-| Checkpoint storage | 135 GiB per partition | 135 GiB per partition |
-| Available system RAM | 200 GiB minimum | 200 GiB minimum |
-| Recommended system RAM | 384 GiB | 384 GiB |
-
-`FL2VA` and `Ref2VA` are separate 135 GiB checkpoint partitions. Start one
-server at a time. DLO keeps rank-local weights in pinned host memory; increasing
-`--dlo-resident-layers` improves latency but does **not** reduce host RAM in the
-current implementation because resident layers retain pinned CPU master copies.
-
-A single RTX 4090 is not covered here. The one-GPU DLO profile in the RTX 5090
-recipe peaked at 26.50 GiB with 12 resident layers, which exceeds 24 GiB. On one
-4090, use the model-level CPU offload command in
-[MiniMax-H3.md](MiniMax-H3.md#single-gpu-accuracy-and-memory-first) instead, or
-lower the resident count and re-measure before trusting it.
-
-> **Modular H3:** after #5720 lands, preserve this recipe's one-partition
-> behavior with `--task-type fl2va` or `--task-type ref2va`.
-
-## Two RTX 4090s: 1024x576, 5 seconds
-
-Use TP2 and 12 resident DiT layers. This is the `rtx4090` profile from the main
-recipe. On two RTX 4090s it peaked at 15,620 MiB per rank for T2VA and
-14,918 MiB per rank for Ref2VA, leaving roughly 9 GiB of headroom per card. See
-[Target-hardware validation](#target-hardware-validation) for the full numbers.
-
-```bash
-export VLLM_WORKER_MULTIPROC_METHOD=spawn
-export VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400
-
-CUDA_VISIBLE_DEVICES=0,1 vllm serve /path/to/MiniMax-H3/FL2VA \
-  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
-  --num-gpus 2 --tensor-parallel-size 2 --text-encoder-tp-size 2 \
-  --usp 1 --ring 1 --vae-patch-parallel-size 2 \
-  --vae-parallel-mode tile --vae-use-tiling \
-  --enable-distributed-layerwise-offload --dlo-no-use-allgather \
-  --dlo-resident-layers 12 --enforce-eager \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-For Ref2VA, stop the FL2VA server and restart the same command with
-`/path/to/MiniMax-H3/Ref2VA`. Ref2VA reference image count and prompt length can
-increase activation memory; begin with one request at a time.
-
-`VLLM_OMNI_VIDEO_SYNC_TIMEOUT` matters more here than on larger cards. DLO
-streams non-resident DiT blocks over PCIe on every denoising step, so a 60-step
-request takes several minutes and would otherwise hit the 600-second default.
-
-## Four RTX 4090s: 1024x576, 5 seconds
-
-Keep TP2 and raise Ulysses sequence parallel to 2 so the world size is
-`TP × USP = 4`. Text-encoder TP and VAE patch parallel follow the GPU count.
-Resident layers stay at 12: adding USP does not shard DiT weights further, so
-per-GPU peak HBM stays close to the two-GPU profile while wall-clock improves.
-
-```bash
-export VLLM_WORKER_MULTIPROC_METHOD=spawn
-export VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400
-
-CUDA_VISIBLE_DEVICES=0,1,2,3 vllm serve /path/to/MiniMax-H3/FL2VA \
-  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
-  --num-gpus 4 --tensor-parallel-size 2 --text-encoder-tp-size 4 \
-  --usp 2 --ring 1 --vae-patch-parallel-size 4 \
-  --vae-parallel-mode tile --vae-use-tiling \
-  --enable-distributed-layerwise-offload --dlo-no-use-allgather \
-  --dlo-resident-layers 12 --enforce-eager \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-For Ref2VA, stop the FL2VA server and restart the same command with
-`/path/to/MiniMax-H3/Ref2VA`. Pin four dedicated GPUs; if the launcher exposes
-fewer than four devices, startup fails with
-`Stage 0 requires 4 device(s) based on parallel_config`.
-
-## Target-hardware validation
-
-Measured on RTX 4090 (24,564 MiB each, driver 580.126.09) with the serve
-commands above, at vLLM-Omni `0.26.1.dev55+g81b48e83e`, vLLM `0.26.0`, and
-PyTorch `2.11.0+cu130`. GPUs used by each server were dedicated. `Client E2E`
-and `Peak per GPU` come from the `/v1/videos/sync` response headers
-`x-inference-time-s` and `x-peak-memory-mb`; the latter is the rank-0 CUDA
-reserved high-water mark, so it is a per-GPU figure.
-
-| GPUs | Topology | Task | Shape | Frames | Steps | Client E2E | Peak per GPU | Output validation |
-| ---: | --- | --- | ---: | ---: | ---: | ---: | ---: | --- |
-| 2 | TP2 × USP1 | T2VA (`FL2VA`) | 1024x576 | 124 at 24 FPS | 60 | 7 min 9 s | 15.3 GiB | H.264 video + 32 kHz stereo AAC; full `ffmpeg` decode passed |
-| 2 | TP2 × USP1 | Ref2VA | 1024x576 | 124 at 24 FPS | 60 | 14 min 52 s | 14.6 GiB | H.264 video + 32 kHz stereo AAC; full `ffmpeg` decode passed |
-| 4 | TP2 × USP2 | T2VA (`FL2VA`) | 1024x576 | 124 at 24 FPS | 60 | 4 min 29 s | 15.2 GiB | H.264 video + 32 kHz stereo AAC; full `ffmpeg` decode passed |
-| 4 | TP2 × USP2 | Ref2VA | 1024x576 | 124 at 24 FPS | 60 | 9 min 5 s | 16.1 GiB | H.264 video + 32 kHz stereo AAC; successful `/v1/videos/sync` 200 |
-
-All rows use `seed=1101`, `flow_shift=12`, and `audio_flow_shift=3.0`.
-
-Two-GPU repeats: T2VA measured 434.9 s and 429.3 s; Ref2VA measured 891.9 s and
-892.1 s. Peak memory was identical across repeats for both tasks, and the two
-outputs of each pair agreed to within 115 bytes.
-
-Four-GPU T2VA repeats: 273.8 s and 269.5 s, peaking at 15,560 MiB and
-15,612 MiB. Four-GPU Ref2VA is a single successful end-to-end run (545.2 s,
-16,448 MiB). Follow-up Ref2VA requests on this build completed diffusion but
-then hit the engine's hardcoded 30 s async output wait
-(`_ASYNC_OUTPUT_TIMEOUT` in `diffusion_engine.py`) during post-compute D2H,
-so they are not reported as repeats.
-
-Relative to the two-GPU baseline on the same shape, four-GPU TP2×USP2 was about
-1.6× faster for both tasks, while per-GPU peak HBM stayed in the mid-15 GiB
-range because USP does not further shard resident DiT weights. These are
-single-request validation runs, not concurrent throughput benchmarks.
-
-## Request examples
-
-`t2va` requires an explicit `aspect_ratio`. Without it the request fails with
-`t2va requires an explicit aspect_ratio`, even when `width` and `height` are set.
-
-Text to video and audio, against the `FL2VA` server:
-
-```bash
-curl -sS -D headers_t2va.txt -o out_t2va.mp4 --max-time 14400 \
-  -X POST "http://127.0.0.1:8000/v1/videos/sync" \
-  -F 'prompt=傍晚的小厨房，夕阳余晖从窗边洒进来，旧木桌上放着洗到一半的马克杯和起雾的玻璃瓶，悬挂的抹布轻轻晃动。画面带有手持拍摄的轻微晃动和逆光曝光波动，生活感十足。环境音是安静的厨房底噪。' \
-  -F 'aspect_ratio=16:9' \
-  -F 'width=1024' -F 'height=576' -F 'fps=24' \
-  -F 'num_inference_steps=60' -F 'flow_shift=12' -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":5,"audio_flow_shift":3.0}'
-```
-
-Reference to video and audio, against the `Ref2VA` server:
-
-```bash
-curl -sS -D headers_ref2va.txt -o out_ref2va.mp4 --max-time 14400 \
-  -X POST "http://127.0.0.1:8000/v1/videos/sync" \
-  -F 'prompt=傍晚的小厨房，夕阳余晖从窗边洒进来，旧木桌上放着洗到一半的马克杯和起雾的玻璃瓶，悬挂的抹布轻轻晃动。画面带有手持拍摄的轻微晃动和逆光曝光波动，生活感十足。环境音是安静的厨房底噪。' \
-  -F 'input_reference=@/path/to/reference.jpg;type=image/jpeg' \
-  -F 'audio_reference=</path/to/audio_reference.json' \
-  -F 'width=1024' -F 'height=576' -F 'fps=24' \
-  -F 'num_inference_steps=60' -F 'flow_shift=12' -F 'seed=1101' \
-  -F 'extra_params={"task":"ref2va","duration":5,"audio_flow_shift":3.0}'
-```
-
-`audio_reference` is a JSON object, which is why the example loads it from a file
-with curl's `<` syntax. Its `audio_url` must be an `http(s)` URL or a data URL;
-a bare filesystem path is rejected with `Invalid audio_reference.audio_url`.
-
-```json
-{"audio_url": "https://example.com/reference.wav"}
-```
-
-Reference images are validated before inference: the short edge must be at least
-256 pixels, the long edge at most 5760, and the aspect ratio must fall between
-0.4 and 2.5.
-
-The response headers carry the measurements used in the table above:
-
-```bash
-cat headers_t2va.txt
-ffmpeg -v error -i out_t2va.mp4 -f null - && echo DECODE_OK
-```

recipes/MiniMaxAI/MiniMax-H3-NPU.md

@@ -79,8 +79,7 @@ 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 distributed
-layerwise offload:
+degree 8, native tiled VAE patch parallelism degree 8, and layerwise offload:
 
 ```bash
 export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
@@ -99,7 +98,7 @@ vllm serve "${MODEL}" \
   --usp 8 \
   --ring 1 \
   --text-encoder-tp-size 8 \
-  --enable-distributed-layerwise-offload \
+  --enable-layerwise-offload \
   --vae-parallel-mode tile \
   --vae-use-tiling \
   --vae-patch-parallel-size 8 \
@@ -113,11 +112,6 @@ 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
@@ -140,63 +134,6 @@ 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
@@ -217,8 +154,8 @@ configuration above:
 
 | Workload | Configuration |
 |----------|---------------|
-| 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 |
+| 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 |
 
 These measurements describe the validated shapes rather than a general
 throughput guarantee.

recipes/MiniMaxAI/MiniMax-H3-RTX-PRO-5000.md

@@ -1,198 +0,0 @@
-# MiniMax-H3 on RTX PRO 5000 Blackwell GPUs
-
-This recipe runs MiniMax-H3 in BF16 on 72 GiB RTX PRO 5000 Blackwell GPUs. It
-contains the validated two-GPU DLO configuration and the recommended resident
-configurations: TP1 x Ulysses2 with 20 resident layers on two GPUs, TP2 x
-Ulysses2 on four GPUs, and TP4 x Ulysses2 on eight GPUs. The four- and
-eight-GPU routes do not require offload.
-
-## Capacity requirements
-
-| Resource | Requirement |
-| --- | ---: |
-| GPUs | 2, 4, or 8 x RTX PRO 5000 Blackwell |
-| GPU HBM | 72 GiB per GPU |
-| Checkpoint storage | 135 GiB per partition |
-| Available system RAM | 200 GiB minimum |
-| Recommended system RAM | 384 GiB |
-
-`FL2VA` and `Ref2VA` are separate checkpoint partitions. Start one server at a
-time on a host sized for the minimum system-memory requirement.
-
-## PCIe topology and GPU order
-
-RTX PRO 5000 does not provide NVLink. Before starting the server, identify the
-closest PCIe pairs and their NUMA affinity:
-
-```bash
-nvidia-smi topo -m
-nvidia-smi nvlink -s
-```
-
-For two GPUs, select the closest PCIe pair on one NUMA node. For four GPUs,
-select all cards from one NUMA node. On the validated host,
-physical GPUs `(0,1)` and `(2,3)` are the two `PXB` pairs on NUMA node 0. The
-order `CUDA_VISIBLE_DEVICES=0,2,1,3` maps the Ulysses groups to those local
-pairs. For eight GPUs, the validated order is `0,4,1,5,2,6,3,7`, with host
-memory interleaved across NUMA nodes 0 and 1. Do not copy these IDs blindly:
-reproduce the same PCIe and NUMA relationships on the target host.
-
-## Recommended serving configurations
-
-### Two GPUs
-
-Two 72 GiB cards require distributed layerwise offload. The validated route
-uses TP1 x Ulysses2, keeps 20 leading DiT layers resident, and streams
-rank-local weights without AllGather. Eager execution avoids regional-compile
-instability on this offload path.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8091
-
-CUDA_VISIBLE_DEVICES=0,1 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-numactl --cpunodebind=0 --membind=0 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 2 \
-  --tensor-parallel-size 1 \
-  --usp 2 \
-  --ring 1 \
-  --text-encoder-tp-size 2 \
-  --vae-patch-parallel-size 2 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN \
-  --enable-distributed-layerwise-offload \
-  --dlo-no-use-allgather \
-  --dlo-resident-layers 20 \
-  --enforce-eager
-```
-
-### Four GPUs
-
-The validated baseline uses TP2 x Ulysses2, text-encoder TP4, VAE patch
-parallelism 4, and explicit cuDNN BF16 attention. Selecting the backend
-explicitly keeps the recipe independent of platform-default backend changes.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8091
-
-CUDA_VISIBLE_DEVICES=0,2,1,3 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-numactl --cpunodebind=0 --membind=0 \
-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 GPUs
-
-The recommended eight-GPU route uses TP4 x Ulysses2, text-encoder TP8, VAE
-patch parallelism 8, and host-memory interleaving across both NUMA nodes.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8091
-
-CUDA_VISIBLE_DEVICES=0,4,1,5,2,6,3,7 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-numactl --interleave=0,1 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 8 \
-  --tensor-parallel-size 4 \
-  --usp 2 \
-  --ring 1 \
-  --text-encoder-tp-size 8 \
-  --vae-patch-parallel-size 8 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-For the four- and eight-GPU resident routes, do not add `--enforce-eager`.
-Warm the server once before measuring so regional compilation is outside the
-measured request. The two-GPU DLO route intentionally remains eager.
-
-For Ref2VA, stop the FL2VA server and restart the same command with
-`MODEL="${MODEL_ROOT}/Ref2VA"`.
-
-## Target-hardware validation
-
-All three configurations were exercised on a PCIe-only, dual-socket host with
-eight RTX PRO 5000 GPUs. The run used PyTorch 2.11.0+cu130, CUDA 13.0, driver
-580.95.05, 1344x768 output, 124 frames, and two warmups.
-
-The four-GPU route also received a five-step profiling validation for GPU
-balance:
-
-| Measurement | Result |
-| --- | ---: |
-| Maximum externally sampled peak | 69,219 MiB (67.60 GiB) per GPU |
-| T2VA worker-reported peak | 65,314 MiB |
-| First-frame FL2VA worker-reported peak | 66,780 MiB |
-| T2VA maximum GPU kernel-time deviation | 0.56% |
-| First-frame FL2VA maximum GPU kernel-time deviation | 0.09% |
-
-The recommended routes produced the following 50-step results. MiniMax-H3
-requested 50 denoise steps and executed 49 denoise updates, so per-step latency
-is `denoise / 49`.
-
-| GPUs | Workload | Parallelism | E2E (s) | Text encode (s) | Denoise (s) | VAE decode (s) | Per step (ms) | Peak memory (GiB) |
-| ---: | --- | --- | ---: | ---: | ---: | ---: | ---: | ---: |
-| 2 | T2VA | TP1 x Ulysses2, DLO resident 20 | 515.57 | 1.19 | 504.69 | 8.79 | 10,300 | 36.38 |
-| 2 | FL2VA first-frame I2VA | TP1 x Ulysses2, DLO resident 20 | 553.45 | 1.27 | 541.90 | 8.76 | 11,059 | 36.38 |
-| 4 | T2VA | TP2 x Ulysses2 | 284.01 | 0.03 | 278.73 | 4.36 | 5,688 | 67.58 |
-| 4 | FL2VA first-frame I2VA | TP2 x Ulysses2 | 305.72 | 0.28 | 299.85 | 4.36 | 6,119 | 67.58 |
-| 8 | T2VA | TP4 x Ulysses2 | 163.20 | 0.04 | 159.40 | 2.58 | 3,253 | 45.83 |
-| 8 | FL2VA first-frame I2VA | TP4 x Ulysses2 | 171.62 | 0.27 | 167.25 | 2.57 | 3,413 | 45.83 |
-
-Peak memory is the maximum per-GPU value sampled externally with
-`nvidia-smi`. The two-GPU route leaves about 34.7 GiB below the reported
-73,415 MiB device capacity, the four-GPU route leaves about 4.1 GiB, and the
-eight-GPU route leaves about 25.9 GiB. Re-measure memory for longer reference
-inputs, concurrency greater than one, or a different output shape.
-
-## T2VA request example
-
-```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
-```

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

@@ -1,346 +0,0 @@
-# MiniMax-H3 on RTX PRO 6000 Blackwell GPUs
-
-This recipe runs MiniMax-H3 in BF16 on 96 GiB RTX PRO 6000 Blackwell GPUs.
-The additional HBM over the RTX PRO 5000 profile removes the four-GPU
-minimum: two GPUs are enough to keep the model resident with TP2. Four and
-eight GPUs raise the Ulysses degree to shard the attention sequence further.
-CPU offload and distributed layerwise offload are not required in any of
-these configurations.
-
-Validated on:
-- Host: YLX Y762
-- GPUs: 8 × RTX PRO 6000 Blackwell (96 GiB)
-- Device order: default (`CUDA_VISIBLE_DEVICES` not set)
-- Driver / CUDA: 580.105.08 / 13.0
-- Container image: `vllm/vllm-omni:minimax-h3`
-- Workload: T2VA, 1344×768, `duration=5.0`, 50 steps, `flow_shift=12`, `seed=1101`
-
-## Capacity requirements
-
-| Resource | Two GPUs | Four GPUs | Eight GPUs |
-| --- | ---: | ---: | ---: |
-| GPU HBM | 96 GiB per GPU | 96 GiB per GPU | 96 GiB per GPU |
-| Checkpoint storage | 135 GiB per partition | 135 GiB per partition | 135 GiB per partition |
-| Available system RAM | 200 GiB minimum | 200 GiB minimum | 200 GiB minimum |
-| Recommended system RAM | 384 GiB | 384 GiB | 384 GiB |
-| Measured peak HBM per GPU | 77.49 GiB | 66.44 GiB | 61.07 GiB |
-
-`FL2VA` and `Ref2VA` are separate checkpoint partitions. Start one server at
-a time on a host sized for the minimum system-memory requirement, or pass
-`--task-type fl2va` or `--task-type ref2va` to download and load a single
-partition. The two-server layout described in the eight-GPU section doubles
-both the storage and the host-memory requirement.
-
-## Parallelism summary
-
-| Configuration | TP | Ulysses | Text-encoder TP | VAE patch parallel |
-| --- | ---: | ---: | ---: | ---: |
-| Two GPUs | 2 | 1 | 2 | 2 |
-| Four GPUs | 2 | 2 | 4 | 4 |
-| Eight GPUs | 2 | 4 | 8 | 8 |
-| Eight GPUs, headroom variant | 4 | 2 | 8 | 8 |
-
-Per-GPU weight residency is set by the tensor-parallel degree alone. Raising
-the Ulysses degree lowers activation memory and per-step latency but leaves
-weight residency unchanged. Ring parallelism stays at 1, and H3 is
-CFG-distilled, so `--cfg-parallel-size` must also remain 1.
-
-## PCIe topology and GPU order
-
-RTX PRO 6000 Blackwell does not provide NVLink. Before starting the server,
-inspect the host topology:
-
-```bash
-nvidia-smi topo -m
-nvidia-smi nvlink -s
-```
-
-Tensor-parallel groups are consecutive ranks. Ulysses groups are strided by
-the tensor-parallel degree. Confirm this grouping against the server log
-before tuning the device order on a new host.
-
-For the two-GPU configuration, pick a single `PXB` pair on one NUMA node.
-For the four-GPU configuration, pick two `PXB` pairs on the same node and
-order them so that each Ulysses group lands inside one pair. If physical
-GPUs `(0,1)` and `(2,3)` are the two local pairs, the order is
-`CUDA_VISIBLE_DEVICES=0,2,1,3`. Do not copy these IDs blindly: reproduce the
-same relationship on the target host.
-
-Device-order pinning and NUMA binding are tuning knobs, not prerequisites.
-The measurements in this recipe were taken without either, so any gain from
-them is additional to the numbers reported below and is host-specific.
-
-## Two-GPU serving configuration
-
-Two 96 GiB GPUs hold the BF16 model with TP2 alone. There is no Ulysses
-group, so the DiT attention sequence is not sharded and activation memory is
-higher than in the four-GPU profile at the same output shape. Re-measure
-peak memory before increasing the output shape, the reference-input length,
-or concurrency.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8000
-
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 2 \
-  --tensor-parallel-size 2 \
-  --usp 1 \
-  --ring 1 \
-  --text-encoder-tp-size 2 \
-  --vae-patch-parallel-size 2 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-## Four-GPU serving configuration
-
-Four GPUs keep TP2 for the weight shard and add Ulysses2, which shards the
-attention sequence and lowers per-GPU activation memory. Text-encoder TP4
-and VAE patch parallelism 4 spread the Qwen3-VL encoder and tiled decode
-across all four GPUs. TP1 is not an option on this card: an unsharded BF16
-partition does not fit in 96 GiB.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8000
-
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 4 \
-  --tensor-parallel-size 2 \
-  --usp 2 \
-  --ring 1 \
-  --text-encoder-tp-size 4 \
-  --vae-patch-parallel-size 4 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-## Eight-GPU serving configuration
-
-Eight GPUs extend the Ulysses degree to 4 while keeping TP2. This does not
-lower per-GPU weight residency relative to the four-GPU profile; it lowers
-activation memory and per-step latency by sharding the attention sequence
-four ways.
-
-```bash
-export MODEL_ROOT=/path/to/MiniMax-H3
-export MODEL="${MODEL_ROOT}/FL2VA"
-export PORT=8000
-
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=1800 \
-vllm serve "${MODEL}" \
-  --omni \
-  --host 0.0.0.0 \
-  --port "${PORT}" \
-  --trust-remote-code \
-  --num-gpus 8 \
-  --tensor-parallel-size 2 \
-  --usp 4 \
-  --ring 1 \
-  --text-encoder-tp-size 8 \
-  --vae-patch-parallel-size 8 \
-  --vae-parallel-mode tile \
-  --vae-use-tiling \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-### Rank ordering across two sockets
-
-With TP2 and Ulysses4 the two Ulysses groups are ranks `(0,2,4,6)` and
-`(1,3,5,7)`, and the four tensor-parallel pairs are `(0,1)`, `(2,3)`,
-`(4,5)`, and `(6,7)`. On a dual-socket host these two collectives cannot
-both be socket-local. If you choose to pin the device order, the trade-off
-is:
-
-| Device order | Socket-local collective | Crosses sockets |
-| --- | --- | --- |
-| `0,4,1,5,2,6,3,7` | Ulysses all-to-all | TP all-reduce |
-| `0,1,2,3,4,5,6,7` | TP all-reduce | Ulysses all-to-all |
-
-The first order assumes physical GPUs `0-3` are on NUMA node 0 and `4-7` on
-node 1. Reproduce that relationship on the target host rather than copying
-the IDs. The reported measurements use the default order and no NUMA
-binding; the two orders were not compared on this host.
-
-### Headroom variant: TP4 with Ulysses2
-
-Raising the tensor-parallel degree to 4 halves per-GPU weight residency and
-leaves room for long Ref2VA references, larger output shapes, or
-concurrency greater than one. It also adds a four-way all-reduce per DiT
-block over a link without NVLink. Use it when the TP2 profile runs out of
-headroom, not as the default. Replace the parallel flags above with:
-
-```bash
-  --tensor-parallel-size 4 \
-  --usp 2 \
-```
-
-### Two independent four-GPU servers
-
-An eight-GPU host can instead run one FL2VA server and one Ref2VA server
-side by side, each pinned to its own NUMA node with the four-GPU
-configuration. This removes every cross-socket collective and lifts the
-one-server-at-a-time restriction, at the cost of doubling the requirements
-to 400 GiB available system RAM and 270 GiB of model storage.
-
-Use `CUDA_VISIBLE_DEVICES=0,2,1,3`, `--cpunodebind=0 --membind=0`, and
-`--port 8091` for the FL2VA server. Use `CUDA_VISIBLE_DEVICES=4,6,5,7`,
-`--cpunodebind=1 --membind=1`, and `--port 8092` for the Ref2VA server.
-This layout is described for completeness and was not part of the measured
-runs.
-
-## Shared serving notes
-
-Do not add `--enforce-eager` for a performance run. Warm the server before
-measuring so regional compilation is outside the measured request. On this
-host the first request after startup ran 19% slower than the steady state
-(107.58 s versus 90.48 s on eight GPUs); two warmup requests were enough to
-converge.
-
-For Ref2VA on a single-server layout, stop the FL2VA server and restart the
-same command with `MODEL="${MODEL_ROOT}/Ref2VA"`.
-
-## Attention backend
-
-RTX PRO 6000 Blackwell is an SM120 part, so the datacenter-Blackwell
-`TRTLLM_ATTN` default does not apply here. Every configuration above selects
-cuDNN BF16 attention explicitly. This keeps the recipe independent of
-platform-default backend changes and does not depend on the experimental
-SM120 kernel.
-
-## Optional: online FP8
-
-`--quantization fp8` quantizes eligible DiT linears at load time and is
-compatible with tensor parallelism and VAE tiling. Use it when the resident
-BF16 peak leaves too little headroom for long Ref2VA references, a larger
-output shape, or concurrency greater than one. It cannot be combined with
-layerwise offload.
-
-## Target-hardware validation
-
-T2VA, 1344×768, `duration=5.0`, `fps=24`, 50 steps, `flow_shift=12`,
-`seed=1101`, BF16, `CUDNN_ATTN`, tiled VAE, one request at a time. Servers
-were started with the commands above — default device order, no NUMA
-binding — plus `--enable-diffusion-pipeline-profiler`. Two warmup requests
-preceded each measured request.
-
-| Measurement | Two GPUs | Four GPUs | Eight GPUs |
-| --- | ---: | ---: | ---: |
-| Topology | TP2 × USP1 | TP2 × USP2 | TP2 × USP4 |
-| Text encode | 0.040 s | 0.044 s | 0.035 s |
-| Denoise, 50 steps | 278.55 s | 168.73 s | 87.90 s |
-| Per step | 5.571 s | 3.375 s | 1.758 s |
-| VAE decode | 5.396 s | 2.791 s | 1.798 s |
-| Client E2E | 284.76 s | 172.32 s | 90.48 s |
-| Peak HBM per GPU | 77.49 GiB | 66.44 GiB | 61.07 GiB |
-| Headroom below 96 GiB | 18.5 GiB | 29.6 GiB | 34.9 GiB |
-
-Stage times are read from the `X-Stage-Durations` response header of
-`/v1/videos/sync`. Peak memory is the maximum of `nvidia-smi
---query-gpu=memory.used` sampled at 1 Hz across every device for the
-duration of the measured request. Per step is denoise wall time divided by
-the 50 requested steps. Stage times sum to roughly 0.75 s less than
-end-to-end in all three configurations; queueing, result transfer, and MP4
-muxing sit outside the profiled stages.
-
-### Scaling behaviour
-
-Denoise speedup is not uniform across the sweep: 1.65× from two to four
-GPUs (83% efficiency) but 1.92× from four to eight (96%). Two GPUs run
-Ulysses1, so there is no sequence parallelism at all; going to four GPUs
-pays the one-time cost of introducing the all-to-all, while going from four
-to eight only widens an all-to-all that already exists. Expect the second
-doubling to pay off better than the first on this topology.
-
-VAE decode behaves in the opposite direction — 1.93× from two to four GPUs
-but only 1.55× from four to eight — as patch parallelism produces smaller
-tiles and tile-boundary overhead grows.
-
-Text encoding is 0.04 s in every configuration and is not worth optimising;
-denoise is 96-98% of end-to-end throughout.
-
-### Per-GPU memory model
-
-Peak memory falls by 11.05 GiB from two to four GPUs and by a further
-5.37 GiB from four to eight — halving each time the Ulysses degree doubles,
-because all three configurations shard the DiT with TP2 and hold identical
-weights per GPU. Fitting the first two points gives:
-
-```
-peak HBM per GPU ≈ 55.4 GiB + 22.1 GiB / ulysses_degree
-```
-
-That fit predicts 60.9 GiB at Ulysses4 against 61.07 GiB measured, a 0.25%
-error. The practical consequence is a floor near 55 GiB per GPU: adding
-GPUs past eight will not reduce the per-GPU requirement further. To serve
-on smaller cards, raise the tensor-parallel degree instead.
-
-Re-measure memory for longer reference inputs, concurrency greater than
-one, or a different output shape.
-
-### Not yet measured
-
-Ref2VA latency and memory have not been measured on this host. Ref2VA
-drives the Qwen3-VL presentation from tens of tokens for text-only prompts
-to several thousand with image or video references, so T2VA numbers do not
-transfer to it. The eight-GPU device-order comparison in the section above
-was also not run.
-
-## T2VA request example
-
-`t2va` requires an explicit `aspect_ratio` even when `width` and `height`
-are supplied.
-
-```bash
-export API_URL="http://127.0.0.1:${PORT}/v1/videos/sync"
-
-curl -sS --max-time 1800 -X POST "${API_URL}" \
-  -F 'prompt=At night, three cats march into a bedroom playing tiny brass instruments, then abruptly file out, with synchronized room ambience.' \
-  -F 'width=1344' \
-  -F 'height=768' \
-  -F 'aspect_ratio=16:9' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=50' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":5.0,"audio_flow_shift":3.0}' \
-  -o t2va.mp4
-```
-
-To collect the stage breakdown and peak memory for a request, add
-`--enable-diffusion-pipeline-profiler` to the server command and `-D
-headers.txt` to the curl invocation, then read `X-Stage-Durations` and
-`X-Peak-Memory-MB` from the saved headers.
-
-## Ref2VA request example
-
-`ref2va` defaults to a 16:9 aspect ratio, so `aspect_ratio` is optional
-here.
-
-```bash
-curl -X POST "http://127.0.0.1:${PORT}/v1/videos/sync" \
-  --fail-with-body -w '\nHTTP %{http_code}\n' \
-  --max-time 1200 \
-  -F "input_reference=@/root/hand.jpg;type=image/jpeg" \
-  -F "audio_reference=</root/audio_ref.json" \
-  -F "prompt=2D动画融合在一起的影像。夕阳余晖残留在窗边，生活感十足的小厨房里有旧木桌、洗到一半的马克杯、起雾的玻璃瓶、悬挂的抹布。画面带有智能手机单手拍摄的手抖、近距离对焦的犹豫、逆光曝光波动。要像在家中慌忙拍下某个不可思议事件的自然质感，不要广告影像的精心整理。声音只用厨房环境声与手绘生物柔和的电子音、小小的叫声。" \
-  -F 'width=1344' -F 'height=768' -F 'fps=24' \
-  -F 'num_inference_steps=60' -F 'flow_shift=12' -F 'seed=1101' \
-  -F 'extra_params={"task":"ref2va","duration":8,"audio_flow_shift":3.0}' \
-  -o /root/out_ref2va.mp4
-```

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

@@ -1,262 +0,0 @@
-# MiniMax-H3 on DGX Spark (GB10)
-
-This recipe uses online FP8 weight quantization, tiled VAE decode, and a single
-resident partition. GB10 is a unified-memory platform, so unlike the discrete-GPU
-recipes it uses **no offload of any kind** — see the capacity note below.
-
-Validated on:
-
-- Host: DGX Spark (GB10), aarch64
-- GPUs: 1 (unified memory)
-- Driver: <FILL_DRIVER_VERSION>
-- vLLM: 0.26.0
-- vLLM-Omni: `main` at `e1aa6eae75c460cd1893bc320546e81e66973831`
-- Workloads: T2VA and Ref2VA, 960x576, `duration=8.0`, 50 steps, `flow_shift=12`,
-  `seed=1101`
-
-
-## Capacity requirements
-
-| Resource | DGX Spark (GB10) |
-| --- | ---: |
-| Unified memory | 128 GB LPDDR5X (~121 GiB usable) |
-| GPUs | 1 |
-| Checkpoint storage | 135 GiB per partition |
-| Measured peak allocator high-water, T2VA (FP8) | 97.7 GiB |
-| Measured peak allocator high-water, Ref2VA (FP8) | 102.8 GiB |
-
-`FL2VA` and `Ref2VA` are separate 135 GiB checkpoint partitions. Start one server
-at a time.
-
-On GB10 the CPU and GPU share one physical memory pool, which changes the capacity
-math relative to the RTX and datacenter recipes:
-
-- **Do not use `--enable-distributed-layerwise-offload`.** DLO stages rank-local
-  weights into pinned host memory, which on GB10 is the same pool the weights are
-  already in. Peak usage roughly doubles and the process is killed by the OOM
-  killer (`Exit code: -9`) shortly after `Enabling offloader backend`.
-- **Do not use `--enable-cpu-offload`.** Moving weights from "VRAM" to "host RAM"
-  frees nothing here.
-- **`--quantization fp8` is mandatory.** A BF16 partition is 135 GiB and does not
-  fit in 121 GiB. Online FP8 quantizes the DiT only (62 GiB to ~31 GiB); the
-  Qwen3-VL text encoder and both VAEs stay BF16.
-
-With ~97.7 GiB of the pool held by the allocator at peak, T2VA leaves roughly
-23 GiB of headroom for the OS, page cache, and any other process on the box.
-Ref2VA is tighter on both counts. The allocator high-water rises to 102.8 GiB,
-and the allocator figure understates true pool usage.
-
-Sampling `/proc/meminfo` at 1 Hz across a 50-step Ref2VA request on a host with
-`MemTotal: 127600524 kB` (121.7 GiB), `MemAvailable` started at 8.1 GiB, fell to
-a trough of **7.4 GiB**, and recovered to 8.9 GiB. At the trough the pool held
-roughly **114.3 GiB** — 11.4 GiB more than the 102.8 GiB the allocator reports,
-which is the CUDA context, non-PyTorch allocations, and page cache the header
-does not count.
-
-Treat this platform as strictly single-tenant for Ref2VA. There is no room for a
-second process, and adding reference images, reference videos, or a larger output
-shape will run into the OOM killer.
-
-## One GB10: 960x576, 8 seconds
-
-```bash
-CUDA_VISIBLE_DEVICES=0 \
-FLASHINFER_DISABLE_VERSION_CHECK=1 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=7200 \
-vllm serve /path/to/MiniMax-H3/FL2VA \
-  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
-  --init-timeout 3600 \
-  --num-gpus 1 --tensor-parallel-size 1 --text-encoder-tp-size 1 \
-  --usp 1 --ring 1 --vae-patch-parallel-size 1 \
-  --vae-parallel-mode tile --vae-use-tiling \
-  --quantization fp8 --enforce-eager \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-Wait for `Application startup complete`, then run a short smoke test before
-committing to a full 50-step request.
-
-`t2va` requires an explicit `aspect_ratio` even when `width` and `height` are
-supplied; omitting it fails the request with
-`OmniClientError: t2va requires an explicit aspect_ratio`.
-
-```bash
-curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
-  -F 'prompt=At night, three cats march into a bedroom playing tiny brass instruments, then abruptly file out, with synchronized room ambience.' \
-  -F 'width=960' \
-  -F 'height=576' \
-  -F 'aspect_ratio=16:9' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=10' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":4.0,"audio_flow_shift":3.0}' \
-  -o h3-gb10-smoke.mp4
-```
-
-The full-quality request uses 50 steps:
-
-```bash
-curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
-  -F 'prompt=At night, three cats march into a bedroom playing tiny brass instruments, then abruptly file out, with synchronized room ambience.' \
-  -F 'width=960' \
-  -F 'height=576' \
-  -F 'aspect_ratio=16:9' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=50' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"t2va","duration":8.0,"audio_flow_shift":3.0}' \
-  -o h3-gb10-t2va.mp4
-
-ffprobe -v error -show_entries \
-  stream=index,codec_name,width,height,r_frame_rate,sample_rate,channels \
-  -of json h3-gb10-t2va.mp4
-```
-
-Both requests return `200 OK` with an MP4 body: H.264 video at the requested
-geometry plus a 32 kHz stereo AAC track.
-
-## One GB10: Ref2VA, 960x576, 8 seconds
-
-`FL2VA` and `Ref2VA` are separate 135 GiB partitions and only one fits at a time.
-Stop the FL2VA server before starting this one.
-
-```bash
-CUDA_VISIBLE_DEVICES=0 \
-FLASHINFER_DISABLE_VERSION_CHECK=1 \
-VLLM_WORKER_MULTIPROC_METHOD=spawn \
-VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400 \
-vllm serve /path/to/MiniMax-H3/Ref2VA \
-  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
-  --init-timeout 3600 \
-  --num-gpus 1 --tensor-parallel-size 1 --text-encoder-tp-size 1 \
-  --usp 1 --ring 1 --vae-patch-parallel-size 1 \
-  --vae-parallel-mode tile --vae-use-tiling \
-  --quantization fp8 --enforce-eager \
-  --diffusion-attention-backend CUDNN_ATTN
-```
-
-The 7200 s timeout used for T2VA is too short here: a 50-step Ref2VA request
-takes over an hour on this platform. Use 14400 s.
-
-Unlike `t2va`, `ref2va` defaults to a 16:9 output ratio, so `aspect_ratio` can be
-omitted when `width` and `height` are supplied.
-
-```bash
-curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
-  -D ref2va-headers.txt \
-  -w 'client_e2e_s=%{time_total}\n' \
-  --max-time 14400 \
-  -F 'input_reference=@/path/to/reference.jpg;type=image/jpeg' \
-  -F 'prompt=A hand rests on a wooden table in warm evening light, then slowly opens and turns toward the camera, with quiet room ambience.' \
-  -F 'width=960' \
-  -F 'height=576' \
-  -F 'fps=24' \
-  -F 'num_inference_steps=50' \
-  -F 'flow_shift=12' \
-  -F 'seed=1101' \
-  -F 'extra_params={"task":"ref2va","duration":8.0,"audio_flow_shift":3.0}' \
-  -o h3-gb10-ref2va.mp4
-```
-
-The response is `200 OK` with an MP4 body: H.264 at the requested geometry plus a
-32 kHz stereo AAC track. `ffprobe` reports 8.032 s for `duration=8.0`.
-
-## Measured latency
-
-Single GB10, FP8, eager, cuDNN attention, tiled VAE, one request at a time:
-
-| Workload | Steps | Text encode | Denoise | Per step | VAE decode | MP4 mux | Client E2E | Peak memory |
-| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
-| T2VA, 4 s, smoke shape | 10 | — | — | 8.68 s | — | 0.49 s | 95.9 s | — |
-| T2VA, 8 s, 960x576 | 50 | 0.25 s | 2088 s | 42.61 s | 70 s | 4.84 s | 2169.4 s (36 min 9 s) | 97.7 GiB |
-| Ref2VA, 8 s, 960x576, one image (3 runs) | 10 | 8.43-10.94 s | 665.5-748.8 s | 66.55-74.88 s | 67.9-69.8 s | 3.63 s | 770.3-861.1 s | 102.8 GiB |
-| Ref2VA, 8 s, 960x576, one image | 50 | 9.66 s | 4039.6 s | 80.79 s | 69.4 s | 3.63 s | 4157.0 s (69 min 17 s) | 102.8 GiB |
-
-How these were measured:
-
-- Stage times come from `--enable-diffusion-pipeline-profiler`, read from the
-  `X-Stage-Durations` response header of `/v1/videos/sync`. The keys are
-  `MiniMaxH3Pipeline.encode_prompt` (text encode),
-  `MiniMaxH3Pipeline.diffuse` (denoise), and `MiniMaxH3Pipeline.decode`
-  (VAE decode).
-- MP4 mux is not a header field. It is the
-  `Video response encoding (MP4 bytes)` line in the server log.
-- Peak memory is the `X-Peak-Memory-MB` header, which reports the CUDA allocator
-  high-water mark (`torch.cuda.max_memory_reserved`) for the request. It excludes
-  the CUDA context and non-PyTorch allocations, so true pool usage is somewhat
-  higher. `nvidia-smi --query-gpu=memory.used` is not usable on GB10 — unified
-  memory has no discrete VRAM to report and the field returns `[N/A]`. See the
-  capacity section for a `/proc/meminfo` cross-check.
-- For T2VA, text encode and VAE decode were measured on a separate 10-step run at
-  the same 960x576 / 8 s geometry. Both are independent of step count, so they
-  transfer to the 50-step row unchanged. The Ref2VA MP4 mux figure transfers the
-  same way, from the 10-step run at identical output geometry and duration.
-- Ref2VA peak memory is byte-identical between the 10-step and 50-step runs
-  (`X-Peak-Memory-MB: 105318.000` in both), confirming that peak is set by output
-  geometry and reference input rather than step count.
-- Stage times do not sum exactly to end-to-end. Queueing, result transfer, and
-  engine bookkeeping sit outside the profiled stages.
-
-Denoise dominates at 96% of end-to-end, so step count and geometry are the only
-knobs that materially change the wall clock on this platform.
-
-Ref2VA costs 1.92x the wall clock of T2VA at the same geometry and step count:
-4157.0 s versus 2169.4 s. Text encoding shows the most dramatic ratio — 9.66 s
-versus 0.25 s, 39x — but at 0.2% of end-to-end it is not what makes Ref2VA slow.
-The cost is in denoise. A single reference image expands the Qwen3-VL
-presentation to 6883 tokens (logged as `MiniMax H3 ref2va Qwen presentation:
-6883 tokens, 1 reference images`), and those tokens sit in the attention context
-of every denoise step. Per-step time rises from 42.61 s to 80.79 s, and that
-1.90x multiplies across all 50 steps. VAE decode is unchanged at ~69 s, as
-expected for an identical output shape.
-
-Repeated identical 10-step T2VA requests varied by up to 23% in denoise time
-(397 s to 490 s) on a machine that had already been under sustained load. Treat
-these as single-run measurements on one machine, not a throughput guarantee, and
-expect the slower end of that range for back-to-back jobs.
-
-Ref2VA per-step time is load-dependent in the same way. On an idle machine the
-first 10-step request ran at 66.55 s per step. The 50-step request that followed
-occupied the box for 69 consecutive minutes and averaged 80.79 s per step. Two
-further 10-step requests taken immediately afterwards settled at 74.88 s and
-74.31 s — 12.5% slower than the idle run, and within 0.8% of each other, so this
-is a stable thermal state rather than measurement noise.
-
-Plan for 81 s per step when sizing a full 50-step Ref2VA job; 66 s per step is
-only reachable on a cold machine and does not hold for the length of one request.
-
-Ref2VA text encode converged downward across the four runs (10.94 s, 9.66 s,
-8.52 s, 8.43 s) as first-touch costs fell away; treat ~8.5 s as steady state.
-VAE decode was stable at 67.9-69.8 s throughout.
-
-Set `VLLM_OMNI_VIDEO_SYNC_TIMEOUT` well above the expected request time — the
-default 1800 s is shorter than a 50-step run on this platform, and 7200 s is
-shorter than a 50-step Ref2VA run.
-
-## Known limitations
-
-- One GPU means no Ulysses, ring, TP, or VAE patch parallelism. Pass
-  `--usp 1 --ring 1 --vae-patch-parallel-size 1` explicitly if a profile or
-  script would otherwise supply higher degrees.
-- `--enforce-eager` is used because regional compile adds startup time without a
-  parallelism win on a single rank.
-- `t2va` rejects requests without an explicit `aspect_ratio`. When `width` and
-  `height` are both supplied they take precedence and `aspect_ratio` only has to
-  name one of the supported ratios.
-- Sustained load degrades throughput. See the variance notes above.
-- Only one partition is resident. For Ref2VA, stop the FL2VA server and restart
-  with `/path/to/MiniMax-H3/Ref2VA`. Ref2VA with one reference image is measured
-  above; reference videos and additional images push the token count higher and
-  were not measured. With `MemAvailable` bottoming out at 7.4 GiB during a
-  single-image request, there is very little room to grow — re-measure before
-  adding references or raising the output shape.
-- Ref2VA requires a vLLM-Omni build newer than `v0.26.0`. See the version note
-  under **Validated on**: FP8 weight loading and image-only Ref2VA are both
-  broken on `release/v0.26.0`.suggestion is  `v0.26.1`.
-- Online FP8 is incompatible with layerwise offload — the offload path produces a
-  weight stride the Cutlass FP8 kernel rejects. This is not a practical
-  restriction here since offload is unusable on GB10 anyway.
-```

recipes/MiniMaxAI/MiniMax-H3.md

@@ -750,73 +750,8 @@ 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.
@@ -835,10 +770,6 @@ vllm serve "${MODEL_ROOT}/FL2VA" \
 - A U2 x Ring2 hybrid currently fails with an attention-mask length mismatch; use
   pure Ulysses.
 - Online FP8 is not compatible with layerwise offload.
-- TeaCache and Cache-DiT cannot be enabled on the same server.
-- Image+audio Ref2VA accepts exactly one image and one audio reference.
-- Video Ref2VA accepts one or more video files, but not an additional standalone
-  audio reference.
 - Pure Ulysses still replicates the full DiT on every rank, so smaller-memory GPUs
   cannot use `--usp N --tp 1` as a resident capacity path. Use DiT tensor parallelism
   or model-level CPU offload; text-encoder TP alone is not sufficient.

recipes/OpenBMB/MiniCPM-o-4_5.md

@@ -30,9 +30,8 @@ also provided.
   `hf_config.version="4.5"`):
   - Default single-GPU compatibility layout (auto-loaded):
     [`vllm_omni/deploy/minicpmo_4_5.yaml`](../../vllm_omni/deploy/minicpmo_4_5.yaml)
-  - Recommended 2-GPU continuous-batching layout:
+  - 2-GPU and 3-GPU layouts:
     [`vllm_omni/deploy/minicpmo_4_5_2gpu.yaml`](../../vllm_omni/deploy/minicpmo_4_5_2gpu.yaml),
-  - 3-GPU layout:
     [`vllm_omni/deploy/minicpmo_4_5_3gpu.yaml`](../../vllm_omni/deploy/minicpmo_4_5_3gpu.yaml)
   - 8x RTX 4090 layout:
     [`vllm_omni/deploy/minicpmo_4_5_8x4090.yaml`](../../vllm_omni/deploy/minicpmo_4_5_8x4090.yaml)

recipes/README.md

@@ -19,11 +19,6 @@ add files for this repo. Use one Markdown file per model family by default.
 > Individual pages resolve at `https://recipes.vllm.ai/<provider>/<model-id>`,
 > e.g. [`bosonai/higgs-audio-v3-tts-4b`](https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b).
 
-The `Recipe` column in the Supported Models documentation links to the
-published recipe when available and otherwise to the corresponding recipe in
-this directory. The recipe files remain the source of truth for commands and
-validation details.
-
 Example layout:
 
 ```text
@@ -50,13 +45,11 @@ recipes/
 | [`inclusionAI/Ming-flash-omni-2.0.md`](./inclusionAI/Ming-flash-omni-2.0.md) | Online serving for multimodal chat + standalone TTS | 4x H100 / 1x H100 80GB |
 | [`inclusionAI/Ming-omni-tts.md`](./inclusionAI/Ming-omni-tts.md) | Offline + online dense Ming TTS/audio generation | 1x H100 80GB / 1x AMD MI300X (ROCm 7.2) |
 | [`IndexTeam/IndexTTS-2.md`](./IndexTeam/IndexTTS-2.md) | Online serving for voice-cloned TTS with optional emotion control | 1x L4 24GB or larger CUDA GPU |
-| [`IndexTeam/IndexTTS-2_5.md`](./IndexTeam/IndexTTS-2_5.md) | Online + offline multilingual voice-cloned TTS with native speed and emotion control | 1x NVIDIA H20 96GB |
 | [`MiniMaxAI/MiniMax-H3.md`](./MiniMaxAI/MiniMax-H3.md) | T2VA, FL2VA, image+audio Ref2VA, and multi-video Ref2VA serving | 1x GPU with CPU offload / 4x B300 |
 | [`MiniMaxAI/MiniMax-H3-MUSA.md`](./MiniMaxAI/MiniMax-H3-MUSA.md) | MiniMax H3 T2VA, FL2VA, and Ref2VA on MUSA | 4x MTT S5000 (TP4 Ref2VA profile) |
 | [`krea/Krea-2.md`](./krea/Krea-2.md) | Text-to-image (Turbo + Raw), offline + online, with LoRA | 1x H100 80GB |
 | [`LTX/LTX-2.md`](./LTX/LTX-2.md) | LTX-2/LTX-2.3 text-to-video and image-to-video with synchronized audio | H200 141GB / 96GB-class GPU |
 | [`MammothModa2/MammothModa2.md`](./MammothModa2/MammothModa2.md) | Preview and Dev text-to-image (AR → DiT); Dev text/image understanding | Preview: 1x L40S 48GB / 1x ≥40GB GPU; Dev: 1x NVIDIA GPU with sufficient cache headroom |
-| [`meituan-longcat/LongCat-Video-Avatar-1.5.md`](./meituan-longcat/LongCat-Video-Avatar-1.5.md) | Audio-driven avatar video generation (AT2V / AI2V, single- and multi-speaker, AVC continuation) | 1x H100 80GB |
 | [`mistralai/Voxtral-TTS.md`](./mistralai/Voxtral-TTS.md) | Online serving for TTS | 1x RTX 4090 24GB |
 | [`Robbyant/LingBot-Video.md`](./Robbyant/LingBot-Video.md) | Native dense and MoE text-to-video serving | Dense: 1x L20X; MoE: 1x L20X (~67.7 GiB peak) |
 | [`cosmos3/Cosmos3-Nano.md`](./cosmos3/Cosmos3-Nano.md) | Text-to-image, text-to-video, image-to-video, video-to-video generation, text to video with sound, action policy | 1x H200 141GB / B300 |

recipes/meituan-longcat/LongCat-Video-Avatar-1.5.md

@@ -1,282 +0,0 @@
-# LongCat-Video-Avatar-1.5
-
-> Audio-driven avatar video generation (AT2V / AI2V)
-
-## Summary
-
-- Vendor: meituan-longcat
-- Model: `meituan-longcat/LongCat-Video-Avatar-1.5`
-- Task: Audio-to-video (AT2V) and audio-and-image-to-video (AI2V) avatar generation
-- Mode: Offline inference
-- Maintainer: Community
-
-## When to use this recipe
-
-Use this recipe to drive a talking or singing avatar from a speech clip, either
-from text alone (AT2V) or from a reference image (AI2V), with the native
-LongCat-Video-Avatar-1.5 pipeline in vLLM-Omni. It covers:
-
-1. **Single-speaker AT2V / AI2V** — one 93-frame segment from one audio track.
-2. **AVC continuation** — chained segments that cover a longer audio track.
-3. **Multi-speaker AI2V** — several audio tracks placed on a reference image
-   through speaker bounding boxes.
-
-The example saves an mp4 with the generated frames muxed with the input audio.
-
-## References
-
-- Upstream model card: <https://huggingface.co/meituan-longcat/LongCat-Video-Avatar-1.5>
-- Upstream repository and example assets: <https://github.com/meituan-longcat/LongCat-Video>
-- Related example under `examples/`: [`longcat_video/end2end.py`](../../examples/offline_inference/longcat_video/end2end.py)
-
-## Hardware Support
-
-## CUDA
-
-### 1× NVIDIA H100 (80 GB)
-
-#### Environment
-
-- OS: Linux
-- Python: 3.10+
-- Driver: NVIDIA driver with CUDA 12.x
-- vLLM version: Match the repository requirements for your checkout
-- vLLM-Omni version or commit: Use the commit you are deploying from
-
-#### Prerequisites
-
-Install the LongCat Avatar optional runtime dependencies:
-
-```bash
-pip install "vllm-omni[longcat-video-avatar]"
-```
-
-The example uses the `imageio_ffmpeg` executable installed by vLLM-Omni's
-`imageio[ffmpeg]` dependency.
-
-#### Command
-
-Audio-to-video (AT2V):
-
-```bash
-python examples/offline_inference/longcat_video/end2end.py \
-  --model meituan-longcat/LongCat-Video-Avatar-1.5 \
-  --stage at2v \
-  --audio /path/to/speech.wav \
-  --prompt "A person speaks calmly while facing the camera." \
-  --num-frames 93 \
-  --num-inference-steps 8 \
-  --output longcat_avatar_at2v.mp4
-```
-
-Audio-and-image-to-video (AI2V):
-
-```bash
-python examples/offline_inference/longcat_video/end2end.py \
-  --model meituan-longcat/LongCat-Video-Avatar-1.5 \
-  --stage ai2v \
-  --audio /path/to/speech.wav \
-  --image /path/to/reference.jpg \
-  --prompt "A person speaks calmly while facing the camera." \
-  --num-frames 93 \
-  --num-inference-steps 8 \
-  --output longcat_avatar_ai2v.mp4
-```
-
-#### Official Example Assets
-
-Download the official Avatar example assets:
-
-```bash
-mkdir -p longcat_avatar_assets/assets/avatar/single longcat_avatar_assets/assets/avatar/multi
-
-curl -L -o longcat_avatar_assets/assets/avatar/single/man.mp3 \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/single/man.mp3
-curl -L -o longcat_avatar_assets/assets/avatar/single/man.png \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/single/man.png
-curl -L -o longcat_avatar_assets/assets/avatar/single_example_1.json \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/single_example_1.json
-
-curl -L -o longcat_avatar_assets/assets/avatar/multi/sing.png \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi/sing.png
-curl -L -o longcat_avatar_assets/assets/avatar/multi/sing_man.WAV \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi/sing_man.WAV
-curl -L -o longcat_avatar_assets/assets/avatar/multi/sing_woman.WAV \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi/sing_woman.WAV
-curl -L -o longcat_avatar_assets/assets/avatar/multi/introduce.png \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi/introduce.png
-curl -L -o longcat_avatar_assets/assets/avatar/multi/introduce_man.mp3 \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi/introduce_man.mp3
-curl -L -o longcat_avatar_assets/assets/avatar/multi/introduce_woman.mp3 \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi/introduce_woman.mp3
-curl -L -o longcat_avatar_assets/assets/avatar/multi_example_1.json \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi_example_1.json
-curl -L -o longcat_avatar_assets/assets/avatar/multi_example_2.json \
-  https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/avatar/multi_example_2.json
-
-export LONGCAT_VIDEO_ASSET_DIR="$PWD/longcat_avatar_assets/assets/avatar"
-export AVATAR_MODEL=meituan-longcat/LongCat-Video-Avatar-1.5
-export PROMPT="$(python -c 'import json, os; print(json.load(open(os.environ["LONGCAT_VIDEO_ASSET_DIR"] + "/single_example_1.json"))["prompt"])')"
-```
-
-`--base-model-dir` points at a local LongCat-Video base checkpoint for the
-tokenizer, text encoder and VAE; omit it to download those components from
-Hugging Face.
-
-```bash
-export BASE_MODEL_DIR=/cache/longcat_models/LongCat-Video
-```
-
-#### Official Asset Smoke Test
-
-Audio-to-video with the official audio:
-
-```bash
-python examples/offline_inference/longcat_video/end2end.py \
-  --model "$AVATAR_MODEL" \
-  --base-model-dir "$BASE_MODEL_DIR" \
-  --stage at2v \
-  --audio "$LONGCAT_VIDEO_ASSET_DIR/single/man.mp3" \
-  --prompt "$PROMPT" \
-  --num-frames 93 \
-  --num-inference-steps 8 \
-  --output official_asset_longcat_avatar_at2v.mp4
-```
-
-Audio-and-image-to-video with the official audio and image:
-
-```bash
-python examples/offline_inference/longcat_video/end2end.py \
-  --model "$AVATAR_MODEL" \
-  --base-model-dir "$BASE_MODEL_DIR" \
-  --stage ai2v \
-  --audio "$LONGCAT_VIDEO_ASSET_DIR/single/man.mp3" \
-  --image "$LONGCAT_VIDEO_ASSET_DIR/single/man.png" \
-  --prompt "$PROMPT" \
-  --num-frames 93 \
-  --num-inference-steps 8 \
-  --output official_asset_longcat_avatar_ai2v.mp4
-```
-
-#### Official Single-Speaker AVC Continuation
-
-`--num-segments` chains AVC segments; `auto` covers the full input audio.
-
-```bash
-python examples/offline_inference/longcat_video/end2end.py \
-  --model "$AVATAR_MODEL" \
-  --base-model-dir "$BASE_MODEL_DIR" \
-  --input-json "$LONGCAT_VIDEO_ASSET_DIR/single_example_1.json" \
-  --num-frames 93 \
-  --num-cond-frames 13 \
-  --num-segments 5 \
-  --num-inference-steps 8 \
-  --output official_asset_longcat_avatar_single_example_1_ai2v_5seg.mp4
-```
-
-Replace `--num-segments 5` with `--num-segments auto` to run until the full
-official audio is covered. That is a slow archival validation path rather than a
-regular smoke test: about 24m28s on a Modal H100 for the full
-`single_example_1.json` audio with 8 inference steps.
-
-#### Official Multi-Speaker AI2V
-
-The multi-speaker cases use several audio tracks with speaker masks and optional
-bounding boxes. The command below generates the first 93-frame segment, matching
-the first call to the official `generate_ai2v()`.
-
-```bash
-python examples/offline_inference/longcat_video/end2end.py \
-  --model "$AVATAR_MODEL" \
-  --base-model-dir "$BASE_MODEL_DIR" \
-  --input-json "$LONGCAT_VIDEO_ASSET_DIR/multi_example_1.json" \
-  --num-frames 93 \
-  --num-inference-steps 8 \
-  --output official_asset_longcat_avatar_multi_example_1_ai2v.mp4
-```
-
-Use `multi_example_2.json` for the sequential-speaking case, and add
-`--num-cond-frames 13 --num-segments auto` to cover the full audio with AVC
-continuation.
-
-#### Verification
-
-```bash
-ffprobe -hide_banner longcat_avatar_ai2v.mp4
-```
-
-The output must report one video stream and one audio stream: the example muxes
-the generated frames with the input audio.
-
-#### Notes
-
-**Support matrix**
-
-| Mode | Speakers | Image required | AVC continuation |
-| --- | --- | --- | --- |
-| AT2V | Single | No | Yes |
-| AI2V | Single | Yes | Yes |
-| AT2V | Multi | Not supported | Not supported |
-| AI2V | Multi | Yes | Yes |
-
-Multi-speaker Avatar requires AI2V because speaker bounding boxes and masks are
-defined on a reference image; AT2V with several tracks fails with an explicit
-error. AVC continuation uses full-audio embeddings only when `--num-segments` is
-greater than `1` or set to `auto`; single-segment AT2V/AI2V keeps the shorter
-first-segment audio path.
-
-**Sampling parameters**
-
-| Parameter | LongCat pipeline value | Description |
-| --- | --- | --- |
-| `--num-frames` | `num_frames` | Frames generated per segment. The default is 93 frames, or about 3.72 seconds at 25 FPS. LongCat normalizes other values to the temporal-VAE-compatible `4k+1` form. |
-| `--num-inference-steps` | `steps` | Denoising steps. The distilled Avatar path uses 8 steps. |
-| `--fps` | `save_fps` | Output frame rate, and the rate used to align audio embeddings with video frames. The default is 25 FPS. |
-| `sampling_params.guidance_scale` | `text_guidance_scale` | Classifier-free guidance applied to the text prompt. |
-| `sampling_params.guidance_scale_2` | `audio_guidance_scale` | Classifier-free guidance applied to the speech audio. |
-
-With the distilled LoRA enabled (the default), the pipeline uses 8 inference
-steps and sets both guidance scales to `1.0`. With `--no-use-distill`, the
-example sets both to `4.0`. For AVC continuation every segment holds
-`num_frames` frames, but each segment after the first reuses `num_cond_frames`
-conditioning frames, so the unique frame count is
-`num_frames + (num_segments - 1) * (num_frames - num_cond_frames)`.
-
-**Key flags**
-
-- `--stage`: `at2v` for audio-to-video, `ai2v` for audio-and-image-to-video.
-- `--resolution`: `480p` or `720p`.
-- `--input-json`: official LongCat Avatar JSON case, used for the single-speaker
-  and multi-speaker AI2V examples.
-- `--num-segments`: number of AVC segments, or `auto` to cover the full audio.
-- `--num-cond-frames`: previous-frame conditioning window for AVC continuation.
-- `--use-int8` / `--no-use-int8`: load the official INT8 Avatar DiT weights by
-  default, or full precision weights.
-- `--use-distill` / `--no-use-distill`: enable the official distilled LoRA path
-  by default.
-- `--build-components-on-gpu`: build large Avatar components directly on GPU for
-  faster startup, at a higher peak VRAM cost. Disabled by default.
-- `--base-model-dir`: local LongCat-Video base model directory for the
-  tokenizer, text encoder and VAE components.
-
-**Memory usage**
-
-Measured on a Modal H100 running the official 93-frame AI2V example with the
-INT8 DiT, distilled LoRA and 8 inference steps:
-
-| Component build | CLI option | Peak GPU memory | Model loading time |
-| --- | --- | ---: | ---: |
-| CPU (default) | None | About 41.0 GiB | About 130s |
-| GPU | `--build-components-on-gpu` | About 56.8 GiB | About 33s |
-
-The reported peak covers the end-to-end run. Building components on CPU only
-reduces initialization memory; denoising still runs on GPU. These numbers are
-memory guidance rather than a performance benchmark.
-
-**Known limitations**
-
-- Single GPU only. Cache acceleration, sequence/CFG/tensor parallelism, HSDP,
-  CPU offload, VAE patch parallelism and quantization are not wired up for this
-  pipeline yet; see the diffusion feature matrix in
-  [`docs/user_guide/diffusion_features.md`](../../docs/user_guide/diffusion_features.md).
-- Offline inference only. Online serving is not supported yet.

tests/benchmarks/patch/test_patch.py

@@ -6,21 +6,13 @@ Unit tests for patch.py
 """
 
 import asyncio
-import base64
 import json
-import time
-from types import SimpleNamespace
 
 import pytest
 from pytest_mock import MockerFixture
 from vllm.benchmarks.lib.endpoint_request_func import RequestFuncInput
 
-from vllm_omni.benchmarks.patch.patch import (
-    MixRequestFuncOutput,
-    async_request_openai_chat_omni_completions,
-    async_request_openai_realtime_duplex,
-)
-from vllm_omni.experimental.fullduplex.client import RealtimeEventCollector
+from vllm_omni.benchmarks.patch.patch import MixRequestFuncOutput, async_request_openai_chat_omni_completions
 
 pytestmark = [pytest.mark.core_model, pytest.mark.benchmark, pytest.mark.cpu]
 
@@ -48,156 +40,6 @@ class MockResponse:
         pass
 
 
-@pytest.mark.asyncio
-async def test_seed_tts_realtime_duplex_exports_per_request_metrics(monkeypatch):
-    class FakeRealtimeClient:
-        last_instance = None
-
-        def __init__(self, url):
-            assert url == "ws://localhost:8000/v1/realtime?duplex=1"
-            self.events = RealtimeEventCollector()
-            self.configure_kwargs = None
-            self.sent = []
-            self.response_count = 0
-            self.ack_count = 0
-            type(self).last_instance = self
-
-        async def __aenter__(self):
-            return self
-
-        async def __aexit__(self, *_args):
-            return None
-
-        async def configure(self, model, **kwargs):
-            assert model == "openbmb/MiniCPM-o-4_5"
-            self.configure_kwargs = kwargs
-
-        async def send(self, event):
-            self.sent.append(event)
-            if event["type"] != "response.create":
-                return
-            self.response_count += 1
-            response_id = f"resp-{self.response_count}"
-            now = time.monotonic()
-            self.events.add(
-                {"type": "response.created", "response": {"id": response_id}},
-                received_at_s=now + 0.01,
-            )
-            self.events.add(
-                {
-                    "type": "response.audio_transcript.delta",
-                    "response_id": response_id,
-                    "delta": f"turn {self.response_count}",
-                },
-                received_at_s=now + 0.02,
-            )
-            self.events.add(
-                {
-                    "type": "response.audio.delta",
-                    "response_id": response_id,
-                    "delta": base64.b64encode(b"\x00\x00" * 2400).decode(),
-                    "sample_rate_hz": 24_000,
-                    "metadata": {"audio_duration_ms": 100},
-                },
-                received_at_s=now + 0.03,
-            )
-            self.events.add(
-                {"type": "response.done", "response": {"id": response_id}},
-                received_at_s=now + 0.04,
-            )
-
-        async def acknowledge_playback(self):
-            self.ack_count += 1
-
-        async def close_session(self, **_kwargs):
-            return None
-
-    monkeypatch.setattr(
-        "vllm_omni.benchmarks.patch.patch.RealtimeDuplexClient",
-        FakeRealtimeClient,
-    )
-    request_input = RequestFuncInput(
-        model="openbmb/MiniCPM-o-4_5",
-        model_name="openbmb/MiniCPM-o-4_5",
-        prompt="hello",
-        api_url="http://localhost:8000/v1/realtime",
-        prompt_len=1,
-        output_len=20,
-        logprobs=None,
-        multi_modal_content=None,
-        ignore_eos=False,
-        extra_body={"save_duplex_request_metrics": True},
-    )
-    request_input.seed_tts_speech_extra = {"ref_audio": "data:audio/wav;base64,AAAA"}
-    request_input.seed_tts_system_prompt = "Speak exactly."
-    request_input.seed_tts_turns = tuple(
-        SimpleNamespace(utterance_id=f"utt-{index}", target_text=f"text {index}") for index in range(4)
-    )
-
-    output = await async_request_openai_realtime_duplex(
-        request_input,
-        session=None,
-    )
-
-    client = FakeRealtimeClient.last_instance
-    assert client.configure_kwargs["native_duplex"] is False
-    assert client.configure_kwargs["extra_body"] == {
-        "ref_audio": "data:audio/wav;base64,AAAA",
-    }
-    assert client.sent == [
-        event
-        for index in range(4)
-        for event in (
-            {
-                "type": "conversation.item.create",
-                "item": {
-                    "type": "message",
-                    "role": "user",
-                    "content": [{"type": "input_text", "text": f"text {index}"}],
-                },
-            },
-            {"type": "response.create"},
-        )
-    ]
-    assert client.ack_count == 4
-    assert output.success is True
-    assert output.generated_text == "turn 1 turn 2 turn 3 turn 4"
-    assert output.audio_duration == pytest.approx(0.4)
-    assert output.ttft > 0
-    assert output.audio_ttfp > output.ttft
-    assert output.audio_rtf > 0
-    assert output.latency > 0
-    assert output.tts_turn_pcm_bytes == [b"\x00\x00" * 2400] * 4
-    assert output.tts_output_pcm_bytes == b"\x00\x00" * 9600
-    session_id = output.duplex_request_metrics[0]["session_id"]
-    assert len(output.duplex_request_metrics) == 4
-    for index, metrics in enumerate(output.duplex_request_metrics):
-        assert metrics == {
-            "session_id": session_id,
-            "request_index": index,
-            "utterance_id": f"utt-{index}",
-            "response_id": f"resp-{index + 1}",
-            "source": "client_monotonic_receive",
-            "measurement_origin": {
-                "ttft": "conversation.item.create client send to first non-empty text delta",
-                "ttfp": "conversation.item.create client send to first audio packet",
-                "rtf": "request-start-to-last-audio receive time divided by emitted audio duration",
-            },
-            "ttft_ms": pytest.approx(20.0, abs=2.0),
-            "ttfp_ms": pytest.approx(30.0, abs=2.0),
-            "rtf": pytest.approx(0.3, abs=0.03),
-            "audio_generation_ms": pytest.approx(30.0, abs=2.0),
-            "audio_duration_ms": 100.0,
-        }
-    assert output.duplex_session_metrics == {
-        "session_id": session_id,
-        "audio_turn_count": 4,
-        "mean_ttft_ms": pytest.approx(20.0, abs=2.0),
-        "mean_ttfp_ms": pytest.approx(30.0, abs=2.0),
-        "mean_rtf": pytest.approx(0.3, abs=0.03),
-    }
-
-
 def create_sse_chunk(data_dict):
     """Helper to create SSE formatted chunk"""
     return f"data: {json.dumps(data_dict)}\n\n".encode()

tests/benchmarks/test_accuracy_bench_utils.py

@@ -42,10 +42,7 @@ from benchmarks.accuracy.text_to_image.gbench import (
     summarize_generated_records as summarize_gebench_generated_records,
     summarize_gebench_results,
 )
-from tests.e2e.accuracy.qwen3_omni.qwen3_omni_acc_bench_core import (
-    build_serve_common_argv,
-    seed_tts_bench_argv,
-)
+from tests.e2e.accuracy.qwen3_omni.qwen3_omni_acc_bench_core import seed_tts_bench_argv
 from tests.e2e.accuracy.qwen3_omni.run_qwen_omni_acc_benchmark import sync_dataset_env_from_ns
 from vllm_omni.benchmarks.data_modules.seed_tts_dataset import resolve_seed_tts_root
 
@@ -60,25 +57,6 @@ def test_seed_tts_bench_argv_preserves_hf_repo_id_from_env(monkeypatch):
     assert argv[dataset_idx + 1] == "zhaochenyang20/seed-tts-eval"
 
 
-def test_build_serve_common_argv_accepts_realtime_seed_tts_route(tmp_path):
-    argv = build_serve_common_argv(
-        host="127.0.0.1",
-        port=8000,
-        model="openbmb/MiniCPM-o-4_5",
-        num_prompts=4,
-        max_concurrency=1,
-        num_warmups=0,
-        percentile_metrics="ttft,audio_ttfp,audio_rtf",
-        result_dir=tmp_path,
-        result_filename="result.json",
-        backend="openai-realtime-tts",
-        endpoint="/v1/realtime",
-    )
-
-    assert argv[argv.index("--backend") + 1] == "openai-realtime-tts"
-    assert argv[argv.index("--endpoint") + 1] == "/v1/realtime"
-
-
 def test_sync_dataset_env_preserves_seed_tts_hf_repo_id(monkeypatch):
     ns = argparse.Namespace(
         daily_omni_repo=None,

tests/benchmarks/test_bench_tts_cli.py

@@ -51,14 +51,6 @@ def test_load_model_configs(model_configs_path: Path) -> None:
     assert configs["test/ModelA"]["supported_tasks"] == ["voice_clone", "default_voice"]
 
 
-def test_indextts25_is_registered_in_shared_model_configs() -> None:
-    config_path = Path(bench_tts.__file__).with_name("model_configs.yaml")
-    config = bench_tts.load_model_configs(config_path)["IndexTeam/IndexTTS-2.5"]
-
-    assert config["supported_tasks"] == ["voice_clone"]
-    assert config["task_extra_body"]["voice_clone"]["extra_params"]["lang"] == "en"
-
-
 def test_build_bench_args_voice_clone(model_configs_path: Path) -> None:
     configs = bench_tts.load_model_configs(model_configs_path)
     cmd = bench_tts.build_bench_args(
@@ -128,34 +120,6 @@ def test_build_bench_args_wer_eval_adds_flag(model_configs_path: Path) -> None:
     assert "--seed-tts-wer-eval" in cmd
 
 
-def test_build_bench_args_supports_local_model_and_shared_sweep_options(model_configs_path: Path) -> None:
-    configs = bench_tts.load_model_configs(model_configs_path)
-    cmd = bench_tts.build_bench_args(
-        host="localhost",
-        port=8092,
-        model="test/ModelA",
-        served_model_name="/models/indextts25",
-        task="voice_clone",
-        model_cfg=configs["test/ModelA"],
-        locale="en",
-        num_prompts=500,
-        num_warmups=5,
-        request_seed=42,
-        concurrency=8,
-        dataset_path="/data/seed-tts",
-        wer_eval=False,
-        output_dir=None,
-        result_filename=None,
-        extra_cli_args=["--", "--tokenizer", "/models/indextts25/qwen0.6bemo4-merge"],
-    )
-
-    assert cmd[cmd.index("--model") + 1] == "/models/indextts25"
-    assert cmd[cmd.index("--num-warmups") + 1] == "5"
-    assert cmd[-2:] == ["--tokenizer", "/models/indextts25/qwen0.6bemo4-merge"]
-    extra_body = json.loads(cmd[cmd.index("--extra-body") + 1])
-    assert extra_body == {"task_type": "Base", "seed": 42}
-
-
 def test_unsupported_task_exits(model_configs_path: Path, capsys: pytest.CaptureFixture, mocker) -> None:
     # ModelB does not support voice_design
     mocker.patch.object(

tests/benchmarks/test_seed_tts_dataset_variants.py

@@ -28,13 +28,10 @@ if _MODULE_NAME not in sys.modules:
     _spec.loader.exec_module(_mod)
 
 from vllm_omni.benchmarks.data_modules.seed_tts_dataset import (  # noqa: E402
-    SeedTTSDataset,
     SeedTTSDesignDataset,
     SeedTTSDesignSampleRequest,
-    SeedTTSSampleRequest,
     SeedTTSTextDataset,
     SeedTTSTextSampleRequest,
-    SeedTTSTurn,
 )
 
 # ---------------------------------------------------------------------------
@@ -73,94 +70,6 @@ def mock_tokenizer(mocker):
 # ---------------------------------------------------------------------------
 
 
-def test_seed_tts_dataset_groups_four_turns_with_one_reference(seed_tts_root, mock_tokenizer):
-    ds = SeedTTSDataset(
-        dataset_path=str(seed_tts_root),
-        random_seed=0,
-        locale="en",
-        disable_shuffle=True,
-    )
-
-    requests = ds.sample(
-        mock_tokenizer,
-        num_requests=1,
-        turns_per_session=4,
-        no_oversample=True,
-    )
-
-    assert len(requests) == 1
-    request = requests[0]
-    assert [turn.utterance_id for turn in request.seed_tts_turns] == [
-        "utt000",
-        "utt001",
-        "utt002",
-        "utt003",
-    ]
-    assert [turn.target_text for turn in request.seed_tts_turns] == [
-        "target text 0",
-        "target text 1",
-        "target text 2",
-        "target text 3",
-    ]
-    assert request.seed_tts_speech_extra["ref_text"] == "ref text 0"
-    assert request.seed_tts_ref_wav_path.endswith("utt000.wav")
-
-
-def test_seed_tts_eval_expands_grouped_pcm_by_turn():
-    from vllm_omni.benchmarks.data_modules.seed_tts_eval import (
-        _expand_seed_tts_turn_outputs,
-    )
-
-    request = SeedTTSSampleRequest(
-        prompt="target 0",
-        prompt_len=4,
-        expected_output_len=100,
-        multi_modal_data=None,
-        request_id="session-0",
-        seed_tts_turns=tuple(
-            SeedTTSTurn(utterance_id=f"utt-{index}", target_text=f"target {index}") for index in range(4)
-        ),
-    )
-    output = types.SimpleNamespace(
-        success=True,
-        tts_turn_pcm_bytes=[bytes([index]) for index in range(4)],
-    )
-
-    requests, outputs = _expand_seed_tts_turn_outputs([request], [output])
-
-    assert [item.prompt for item in requests] == [f"target {index}" for index in range(4)]
-    assert [item.seed_tts_utterance_id for item in requests] == [f"utt-{index}" for index in range(4)]
-    assert [item.tts_output_pcm_bytes for item in outputs] == [bytes([index]) for index in range(4)]
-
-
-def test_seed_tts_eval_keeps_session_pcm_for_single_turn_chat():
-    """Chat-omni Seed-TTS sets session PCM only; expand must not wipe it."""
-    from vllm_omni.benchmarks.data_modules.seed_tts_eval import (
-        _expand_seed_tts_turn_outputs,
-    )
-
-    request = SeedTTSSampleRequest(
-        prompt="target 0",
-        prompt_len=4,
-        expected_output_len=100,
-        multi_modal_data=None,
-        request_id="session-0",
-        seed_tts_turns=(SeedTTSTurn(utterance_id="utt-0", target_text="target 0"),),
-    )
-    pcm = b"\x01\x02\x03\x04"
-    output = types.SimpleNamespace(
-        success=True,
-        tts_output_pcm_bytes=pcm,
-        tts_turn_pcm_bytes=None,
-    )
-
-    requests, outputs = _expand_seed_tts_turn_outputs([request], [output])
-
-    assert len(requests) == 1
-    assert requests[0].prompt == "target 0"
-    assert outputs[0].tts_output_pcm_bytes == pcm
-
-
 def test_seed_tts_text_dataset_omits_ref_audio(seed_tts_root, mock_tokenizer):
     ds = SeedTTSTextDataset(
         dataset_path=str(seed_tts_root),

tests/config/test_config_factory.py

@@ -2206,24 +2206,6 @@ class TestBaseConfigInheritance:
 class TestPlatformOverrides:
     """Test platform-specific deploy config overrides."""
 
-    def test_qwen3_omni_musa_clears_parent_quantization_for_audio_stages(self):
-        pipeline = resolve_pipeline_config(
-            "qwen3_omni_moe",
-            Q3_OMNI_ALL_STAGES_HF_CONFIG,
-        )
-        assert isinstance(pipeline, PipelineConfig)
-        deploy_path = Path(get_deploy_config_path("qwen3_omni_moe.yaml"))
-
-        base_stages = merge_pipeline_deploy(pipeline, load_deploy_config(deploy_path))
-        assert "hf_overrides" not in base_stages[1].yaml_engine_args
-        assert "hf_overrides" not in base_stages[2].yaml_engine_args
-
-        musa = _apply_platform_overrides(load_deploy_config(deploy_path), platform="musa")
-        musa_stages = merge_pipeline_deploy(pipeline, musa)
-        expected = {"quantization_config": None}
-        assert musa_stages[1].yaml_engine_args["hf_overrides"] == expected
-        assert musa_stages[2].yaml_engine_args["hf_overrides"] == expected
-
     def test_qwen3_tts_rocm_disables_code2wav_outer_cudagraph(self):
         deploy_path = Path(get_deploy_config_path("qwen3_tts.yaml"))
 
@@ -2259,8 +2241,7 @@ class TestPlatformOverrides:
                 load_deploy_config(Path(get_deploy_config_path(filename))), platform="cuda"
             )
             replica_stages = merge_pipeline_deploy(pipeline, replica)
-            # Explicit null clears the inherited single-GPU 2 GiB CUDA cap.
-            assert replica_stages[1].yaml_engine_args.get("kv_cache_memory_bytes") is None
+            assert replica_stages[1].yaml_engine_args["kv_cache_memory_bytes"] is None
 
     def test_npu_overrides(self):
         deploy_path = Path(get_deploy_config_path("qwen3_omni_moe.yaml"))
@@ -2276,16 +2257,6 @@ class TestPlatformOverrides:
         # Stage 2 unaffected fields stay at base
         assert deploy.stages[2].enforce_eager is False
 
-    def test_qwen2_5_omni_xpu_uses_eager_ar_stages(self):
-        deploy_path = Path(get_deploy_config_path("qwen2_5_omni.yaml"))
-
-        deploy = load_deploy_config(deploy_path)
-        deploy = _apply_platform_overrides(deploy, platform="xpu")
-
-        assert deploy.stages[0].enforce_eager is True
-        assert deploy.stages[1].enforce_eager is True
-        assert deploy.stages[2].enforce_eager is True
-
     def test_xpu_overrides(self):
         deploy_path = Path(get_deploy_config_path("qwen3_omni_moe.yaml"))
         if not deploy_path.exists():

tests/config/test_omni_config.py

@@ -39,7 +39,6 @@ from vllm_omni.config.stage_config import (
     load_deploy_config,
     merge_pipeline_deploy,
 )
-from vllm_omni.diffusion.diffusion_kv.config import DiffusionKVCacheMode
 from vllm_omni.engine.stage_init_utils import build_legacy_engine_args_dict
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -474,8 +473,6 @@ def test_sub_config_fields_match_structured_scopes():
         "moe_backend",
         "hf_overrides",
         "limit_mm_per_prompt",
-        "interleave_mm_strings",
-        "media_io_kwargs",
         "active_stream_window",
         "duplex_max_sessions",
         "enable_sleep_mode",
@@ -969,24 +966,20 @@ def test_diffusion_config_from_kwargs_reuses_legacy_normalization(monkeypatch):
 
     cfg = omni_config_module._DiffusionConfigProjection.from_kwargs(
         diffusion_attention_backend="flash_attn",
-        fa_deterministic=True,
         kv_cache_dtype="fp8",
         kv_cache_skip_steps="0-1",
         kv_cache_skip_layers=[2],
         static_lora_scale=0.25,
-        diffusion_kv_mode="paged_scheduler",
         diffusers_load_kwargs=None,
         diffusers_call_kwargs=None,
     )
 
     assert cfg.diffusion_attention_config.default.backend == "flash_attn"
-    assert cfg.fa_deterministic is True
     assert cfg.diffusion_kv_cache_dtype == "fp8"
     assert cfg.diffusion_kv_cache_skip_step_indices == {0, 1}
     assert cfg.diffusion_kv_cache_skip_layer_indices == {2}
     assert cfg.lora_scale == 0.25
     assert cfg.cache_backend == "tea_cache"
-    assert cfg.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
     assert cfg.diffusers_load_kwargs == {}
     assert cfg.diffusers_call_kwargs == {}
 
@@ -1001,8 +994,6 @@ def test_from_pipeline_config_normalizes_diffusion_config_aliases_from_engine_ar
                 "stages:",
                 "  - stage_id: 0",
                 "    diffusion_attention_backend: flash_attn",
-                "    fa_deterministic: true",
-                "    diffusion_kv_mode: paged_scheduler",
             ]
         )
     )
@@ -1014,29 +1005,6 @@ def test_from_pipeline_config_normalizes_diffusion_config_aliases_from_engine_ar
 
     assert isinstance(stage, VllmOmniDiffusionStageConfig)
     assert stage.diffusion_config.diffusion_attention_config.default.backend == "flash_attn"
-    assert stage.diffusion_config.fa_deterministic is True
-    assert stage.diffusion_config.diffusion_kv_mode is DiffusionKVCacheMode.PAGED_SCHEDULER
-
-
-def test_from_pipeline_config_rejects_reserved_diffusion_kv_mode(tmp_path):
-    deploy_path = tmp_path / "dreamzero_reserved_diffusion_kv.yaml"
-    deploy_path.write_text(
-        "\n".join(
-            [
-                "pipeline: dreamzero",
-                "async_chunk: false",
-                "stages:",
-                "  - stage_id: 0",
-                "    diffusion_kv_mode: paged_worker_local",
-            ]
-        )
-    )
-
-    with pytest.raises(ValueError, match="reserved but not implemented"):
-        _from_pipeline_key(
-            "dreamzero",
-            deploy_config_path=str(deploy_path),
-        )
 
 
 def test_diffusion_config_field_classification_covers_current_fields():
@@ -1057,7 +1025,6 @@ def test_diffusion_config_field_classification_covers_current_fields():
         "enable_session_state_manager",
         "prompt_embed_cache_size",
         "diffusion_kv_cache_dtype",
-        "diffusion_kv_mode",
     } <= omni_config_module._DIFFUSION_ONLY_CONFIG_FIELDS
     assert {
         "revision",

tests/core/sched/test_omni_ar_scheduler_logprobs.py

@@ -92,9 +92,6 @@ class _Request:
         self.num_computed_tokens = 0
         self.num_in_flight_tokens = 0
         self.num_output_placeholders = 0
-        # vLLM 0.27 (a0c092ee72): Request gained num_stale_output_tokens to
-        # track in-flight outputs discarded at preemption/streaming-stop.
-        self.num_stale_output_tokens = 0
         self.has_encoder_inputs = False
         self.pooling_params = None
         self.resumable = True

tests/core/sched/test_omni_ar_scheduler_stale_drain.py

@@ -1,223 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-"""Investigation tests for the num_stale_output_tokens drain (59b9e719).
-
-The seed-TTS WER regression appeared with the vLLM 0.27 rebase (nightly
-2946 -> 2949: mean WER 0.2695 -> 0.3936, median 0.0 in both), whose prime
-suspect is the reimplemented async-token discard: vLLM 0.26 drained
-``async_tokens_to_discard`` one arriving frame at a time and suppressed
-only the token append; the 0.27 adaptation seeds
-``num_stale_output_tokens`` with the discarded *placeholder count* and
-drains it by each arriving frame's ``num_tokens_scheduled``, dropping the
-whole per-request update. Whenever seed and arrivals disagree, the counter
-outlives the old segment and the drain consumes *valid* frames of the new
-segment — a hole in the talker's codec stream (garbled audio, text/audio
-mismatch) — or underflows its own assert on the new segment's prefill
-frame (engine-core death mid-step).
-
-The fix seeds the counter from ``num_in_flight_tokens`` — the same
-scheduled-token units the drain subtracts — so every pre-discard frame
-drains exactly its own contribution and new-segment frames can never be
-swallowed. These tests pin that contract one frame at a time; the
-delivered / swallowed observable is whether ``_update_request_with_output``
-runs for the frame.
-"""
-
-from __future__ import annotations
-
-from types import SimpleNamespace
-from unittest.mock import MagicMock
-
-import pytest
-
-# Imports must run in this order: vllm_omni applies patches to vllm.v1.request
-# before Request / StreamingUpdate are bound in this module.
-# isort: off
-import vllm_omni  # noqa: F401 - import for side effects (patch vLLM)
-from vllm.sampling_params import SamplingParams
-from vllm.v1.core.sched.output import SchedulerOutput
-from vllm.v1.outputs import ModelRunnerOutput
-from vllm.v1.request import Request, RequestStatus, StreamingUpdate
-from vllm_omni.core.sched.omni_ar_scheduler import OmniARScheduler
-
-# isort: on
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-
-
-def _make_session() -> Request:
-    session = Request(
-        request_id="req-stale-drain-test",
-        prompt_token_ids=[1, 2, 3],
-        sampling_params=SamplingParams(max_tokens=32),
-        pooling_params=None,
-        arrival_time=100.0,
-        block_hasher=None,
-    )
-    session.status = RequestStatus.RUNNING
-    if not hasattr(session, "num_stale_output_tokens"):
-        # vLLM 0.27 defines this Request field; 0.26 (local dev) does not.
-        session.num_stale_output_tokens = 0
-    if not hasattr(session, "num_in_flight_tokens"):
-        session.num_in_flight_tokens = 0
-    return session
-
-
-def _replace_streaming_session(session: Request) -> None:
-    """Run the real stage-0 streaming replacement (the discard/seed site)."""
-    sched = OmniARScheduler.__new__(OmniARScheduler)
-    sched._new_prompt_len_snapshot = {}
-    sched.vllm_config = SimpleNamespace(model_config=SimpleNamespace(stage_id=0))
-    sched.num_waiting_for_streaming_input = 0
-    sched.log_stats = False
-    sched.chunk_transfer_adapter = None
-    sched.skipped_waiting = set()
-    session.status = RequestStatus.WAITING_FOR_STREAMING_REQ
-    update = StreamingUpdate(
-        mm_features=None,
-        prompt_token_ids=[10, 20],
-        max_tokens=32,
-        arrival_time=200.0,
-        sampling_params=SamplingParams(max_tokens=16),
-    )
-    sched._update_request_as_session(session, update)
-    session.status = RequestStatus.RUNNING
-
-
-def _make_drain_sched(session: Request) -> MagicMock:
-    sched = MagicMock()
-    sched.requests = {session.request_id: session}
-    sched.perf_metrics = None
-    sched.structured_output_manager.should_advance.return_value = False
-    sched._update_request_with_output.return_value = ([42], False)
-    sched._process_kv_transfer_trigger.return_value = False
-    sched.chunk_transfer_adapter = MagicMock()
-    sched.running = [session]
-    sched.waiting_for_transfer_free = set()
-    sched.transfer_triggered_requests = set()
-    sched.active_kv_transfers = set()
-    sched.pending_stop_after_extraction = set()
-    sched.connector = None
-    sched.kv_cache_manager.take_events.return_value = None
-    sched.finished_req_ids_dict = {}
-    sched.make_stats.return_value = None
-    return sched
-
-
-def _run_step(sched: MagicMock, session: Request, *, num_scheduled: int, token: int) -> bool:
-    """Feed one model-runner frame through update_from_output.
-
-    Returns True when the frame's tokens were delivered (the append ran),
-    False when the frame was swallowed by the stale drain.
-    """
-    scheduler_output = MagicMock(spec=SchedulerOutput)
-    scheduler_output.num_scheduled_tokens = {session.request_id: num_scheduled}
-    scheduler_output.scheduled_spec_decode_tokens = {}
-    scheduler_output.num_invalid_spec_tokens = 0
-
-    model_runner_output = MagicMock(spec=ModelRunnerOutput)
-    model_runner_output.sampled_token_ids = [[token]]
-    model_runner_output.logprobs = None
-    model_runner_output.prompt_logprobs_dict = {}
-    model_runner_output.pooler_output = None
-    model_runner_output.num_nans_in_logits = None
-    model_runner_output.kv_connector_output = None
-    model_runner_output.cudagraph_stats = None
-    model_runner_output.req_id_to_index = {session.request_id: 0}
-    model_runner_output.routed_experts = None
-    model_runner_output.inter_stage_outputs = None
-
-    sched._update_request_with_output.reset_mock()
-    OmniARScheduler.update_from_output(sched, scheduler_output, model_runner_output)
-    return sched._update_request_with_output.called
-
-
-def test_exact_drain_delivers_new_segment_frame() -> None:
-    """One in-flight decode frame at replacement: its late output drains the
-    counter exactly and the new segment's first frame is delivered."""
-    session = _make_session()
-    session.append_output_token_ids([7, 8, 9])
-    session.num_computed_tokens = 6
-    session.num_output_placeholders = 1
-    session.num_in_flight_tokens = 1
-
-    _replace_streaming_session(session)
-    assert session.num_stale_output_tokens == 1
-
-    sched = _make_drain_sched(session)
-    assert _run_step(sched, session, num_scheduled=1, token=42) is False  # late frame dropped
-    assert session.num_stale_output_tokens == 0
-    assert _run_step(sched, session, num_scheduled=1, token=43) is True  # new segment survives
-
-
-def test_two_in_flight_frames_drain_without_swallowing() -> None:
-    """Two in-flight decode frames: both late frames drop, the new segment's
-    first valid frame is delivered. A placeholder-based seed swallowed it
-    whenever fewer frames arrived than placeholders counted (the driver of
-    the seed-TTS WER regression, nightly 2946 -> 2949: 0.2695 -> 0.3936)."""
-    session = _make_session()
-    session.append_output_token_ids([7, 8, 9])
-    session.num_computed_tokens = 7
-    session.num_output_placeholders = 2
-    session.num_in_flight_tokens = 2
-
-    _replace_streaming_session(session)
-    assert session.num_stale_output_tokens == 2
-
-    sched = _make_drain_sched(session)
-    assert _run_step(sched, session, num_scheduled=1, token=42) is False  # late frame 1
-    assert _run_step(sched, session, num_scheduled=1, token=44) is False  # late frame 2
-    assert session.num_stale_output_tokens == 0
-
-    delivered = _run_step(sched, session, num_scheduled=1, token=43)  # new segment, frame 1
-    assert delivered is True, (
-        "valid new-segment frame was swallowed by leftover stale count "
-        f"(num_stale_output_tokens left at {session.num_stale_output_tokens})"
-    )
-
-
-def test_spec_placeholder_asymmetry_does_not_swallow_valid_frame() -> None:
-    """Placeholder counts can exceed scheduled counts (e.g. a draft
-    invalidated before execution): 1 in-flight MTP frame scheduled 2 tokens
-    but contributed 3 placeholders. Seeding from num_in_flight_tokens keeps
-    seed == drain, so the new segment's valid frame is delivered."""
-    session = _make_session()
-    session.append_output_token_ids([7])
-    session.num_computed_tokens = 7
-    session.num_output_placeholders = 3  # 1 sampled + 2 spec placeholders
-    session.num_in_flight_tokens = 2  # the frame actually scheduled 1 + 1 tokens
-
-    _replace_streaming_session(session)
-    assert session.num_stale_output_tokens == 2
-
-    sched = _make_drain_sched(session)
-    assert _run_step(sched, session, num_scheduled=2, token=42) is False  # late MTP frame
-    assert session.num_stale_output_tokens == 0
-    delivered = _run_step(sched, session, num_scheduled=1, token=43)  # new segment, frame 1
-    assert delivered is True, (
-        "valid new-segment frame swallowed after spec placeholder asymmetry "
-        f"(num_stale_output_tokens left at {session.num_stale_output_tokens})"
-    )
-
-
-def test_in_flight_prefill_chunk_drains_exactly_without_underflow() -> None:
-    """An in-flight prefill chunk carries no placeholders but 5 scheduled
-    tokens. The placeholder-based seed missed it entirely (its late output
-    was appended to the rolled-back session) and any leftover counter
-    underflowed 'assert num_stale_output_tokens >= 0' on the chunk's arrival,
-    killing the engine-core step. Seeding from num_in_flight_tokens drops the
-    late chunk and drains to exactly zero."""
-    session = _make_session()
-    session.append_output_token_ids([7, 8, 9])
-    session.num_computed_tokens = 7
-    session.num_output_placeholders = 0  # prefill chunk: no placeholders
-    session.num_in_flight_tokens = 5  # the chunk's scheduled tokens
-
-    _replace_streaming_session(session)
-    assert session.num_stale_output_tokens == 5
-
-    sched = _make_drain_sched(session)
-    assert _run_step(sched, session, num_scheduled=5, token=42) is False  # late prefill chunk dropped
-    assert session.num_stale_output_tokens == 0
-    assert _run_step(sched, session, num_scheduled=1, token=43) is True  # new segment survives