anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

docs: preserve quantization URLs and recipe coverage

Browse Source 
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu committed 2026-08-10 12:41:11 +08:00
1 parent c588208cc6
commit d10bf78c60
6 files changed
+499 -90
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/mkdocs/hooks/generate_examples.py
+54 -12
View File
@@ -24,6 +24,16 @@ SERVING_MODE_TITLES = {
"online_serving": "Online serving",
}
# Generated example pages keep their source-derived URLs even when their
# navigation category changes. Quantization helpers are feature documentation,
# not user-serving examples, so keep them under the existing Features /
# Quantization section instead of creating a second top-level Quantization
# category under Examples.
EXAMPLE_NAV_TARGETS = {
"quantization": "quantization",
}
GENERATED_QUANTIZATION_EXAMPLES_TITLE = "Generated Examples"
def load_model_display_names() -> dict[str, str]:
try:
@@ -340,26 +350,58 @@ def update_nav_file(examples: list[Example]):
examples_by_category[category] = []
examples_by_category[category].append(example)
# Build the new Examples section - start with preserved items
examples_section = preserved_items.copy()
# Add examples grouped by category, sorted by category name
for category in sorted(examples_by_category.keys()):
category_examples = sorted(examples_by_category[category], key=lambda e: e.path.stem)
category_items = []
for example in category_examples:
def category_items(category: str) -> list[dict[str, str]]:
items = []
for example in sorted(examples_by_category[category], key=lambda e: e.path.stem):
doc_path = EXAMPLE_DOC_DIR / example.category / f"{example.path.stem}.md"
rel_path = doc_path.relative_to(ROOT_DIR / "docs")
category_items.append({example.nav_title: rel_path.as_posix()})
items.append({example.nav_title: rel_path.as_posix()})
return items
if category_items:
# Format category name (e.g., "offline_inference" -> "Offline Inference")
# Build the new Examples section - start with preserved items. Categories
# not explicitly routed elsewhere retain the historical Examples behavior.
examples_section = preserved_items.copy()
for category in sorted(examples_by_category.keys()):
if EXAMPLE_NAV_TARGETS.get(category, "examples") != "examples":
continue
items = category_items(category)
if items:
category_title = fix_case(category.replace("_", " ").title())
examples_section.append({category_title: category_items})
examples_section.append({category_title: items})
# Update the nav structure
nav_list[user_guide_idx]["User Guide"][examples_idx]["Examples"] = examples_section
features_content = next(
(item["Features"] for item in user_guide_content if isinstance(item, dict) and "Features" in item),
None,
)
quantization_content = None
if isinstance(features_content, list):
quantization_content = next(
(item["Quantization"] for item in features_content if isinstance(item, dict) and "Quantization" in item),
None,
)
if isinstance(quantization_content, list):
# Remove only the group owned by this hook so repeated builds are
# idempotent and hand-authored Quantization navigation is retained.
quantization_content[:] = [
item
for item in quantization_content
if not (isinstance(item, dict) and GENERATED_QUANTIZATION_EXAMPLES_TITLE in item)
]
quantization_examples = examples_by_category.get("quantization")
if quantization_examples:
if not isinstance(quantization_content, list):
logger.warning(
"Could not find 'User Guide' -> 'Features' -> 'Quantization' section; "
"omitting generated quantization examples from navigation"
)
else:
quantization_content.append({GENERATED_QUANTIZATION_EXAMPLES_TITLE: category_items("quantization")})
# Write back to file
nav_data["nav"] = nav_list
with open(NAV_FILE, "w", encoding="utf-8") as f:
docs/models/recipe_coverage.yaml
+73
View File
@@ -0,0 +1,73 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# This registry is keyed by an exact Hugging Face checkpoint and task. A
# Supported Models row may cover several checkpoints, but coverage entries must
# be split whenever the example or recipe differs.
version: 1
# The registry is incrementally audited. An absent entry means that coverage
# has not been audited yet; it is not evidence that no recipe exists. Do not
# infer recipe coverage from the implementation or hardware columns in
# supported_models.md.
entries:
- model: Qwen/Qwen3-Omni-30B-A3B-Instruct
task: omni-serving
examples:
- docs/user_guide/examples/offline_inference/qwen3_omni.md
- docs/user_guide/examples/online_serving/qwen3_omni.md
recipe:
status: repository
repository_path: recipes/Qwen/Qwen3-Omni.md
hardware: [nvidia]
- model: Qwen/Qwen-Image
task: text-to-image
examples:
- docs/user_guide/examples/offline_inference/text_to_image.md
- docs/user_guide/examples/online_serving/text_to_image.md
recipe:
status: published
published_url: https://recipes.vllm.ai/Qwen/Qwen-Image
repository_path: recipes/Qwen/Qwen-Image.md
hardware: [nvidia]
- model: Qwen/Qwen-Image-2512
task: text-to-image
examples:
- docs/user_guide/examples/offline_inference/text_to_image.md
- docs/user_guide/examples/online_serving/text_to_image.md
recipe:
status: repository
repository_path: recipes/Qwen/Qwen-Image-2512.md
hardware: [nvidia]
- model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
task: text-to-speech
examples:
- docs/user_guide/examples/offline_inference/text_to_speech.md
- docs/user_guide/examples/online_serving/text_to_speech.md
recipe:
status: published
published_url: https://recipes.vllm.ai/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
repository_path: recipes/Qwen/Qwen3-TTS.md
hardware: [nvidia]
- model: bosonai/higgs-audio-v3-tts-4b
task: text-to-speech
examples:
- docs/user_guide/examples/online_serving/text_to_speech.md
recipe:
status: published
published_url: https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b
repository_path: recipes/BosonAI/Higgs-Audio-V3-TTS.md
hardware: [nvidia]
- model: MiniMaxAI/MiniMax-H3
task: video-audio-generation
examples: []
recipe:
status: published
published_url: https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3
repository_path: recipes/MiniMaxAI/MiniMax-H3.md
hardware: [nvidia, amd]
docs/models/supported_models.md
+112 -78
View File
@@ -17,87 +17,121 @@ th {
}
</style>
| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU |
|--------------|--------|-------------------|------------|---------|-----|-----------|
| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ | | | |
| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ |
| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | |
| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | |
| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | |
| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | |
| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ | | | |
| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | |
| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | |
| `LingBotVideoPipeline` | LingBot-Video dense and MoE 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` | ✅︎ | | | |
| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | |
| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | |
| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ |
| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | |
| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ |
| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ |
| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | |
| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | |
| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | |
| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ |
| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ |
| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ |
| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ |
| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | |
| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | |
| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | |
| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | |
| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | |
| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | |
| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | |
| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | |
| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | |
| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | |
| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ |
| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | |
| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | |
| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | |
| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ |
| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | |
| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | |
| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | |
| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | |
| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | |
| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | |
| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | |
|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | |
| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | |
| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | |
| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU | Recipe |
|--------------|--------|-------------------|------------|---------|-----|-----------|--------|
| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen3-Omni.md) |
| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ | | | | — |
| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ | — |
| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | | — |
| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | | — |
| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen-Image) |
| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen-Image-2512.md) |
| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | | — |
| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | | — |
| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ | | | | — |
| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | | — |
| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | | — |
| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2I, T2V, TI2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | | — |
| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | ✅︎ | | | [Published](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3) |
| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | | — |
| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | | — |
| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ | — |
| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | | — |
| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ | — |
| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ | — |
| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | | — |
| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | | — |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | | — |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | | — |
| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | | — |
| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ | — |
| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ | — |
| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ | — |
| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ | — |
| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | | — |
| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | | — |
| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | | — |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | | — |
| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | | — |
| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | | — |
| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | | — |
| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | | — |
| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | | — |
| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | | [Published](https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b) |
| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | | — |
| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ | — |
| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | | — |
| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | | — |
| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | | — |
| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ | — |
| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | | — |
| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | | — |
| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | | — |
| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | | — |
| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | | — |
| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | | — |
| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | | — |
|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | | — |
| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | | — |
| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | | — |
The `Recipe` column links the exact checkpoint/task entry from
[`recipe_coverage.yaml`](https://github.com/vllm-project/vllm-omni/blob/main/docs/models/recipe_coverage.yaml).
`Published` is preferred when a corresponding `recipes.vllm.ai` page exists;
otherwise the link points to the repository recipe. `—` means that the exact
checkpoint/task mapping has not been audited 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 coverage is audited.
✅︎ indicates the model is supported on that backend. Empty cells mean not listed as supported on that backend.
## Recipe and Example Coverage
The table above describes implementation and backend support. It does not
imply that a model has a validated deployment recipe.
Recipe and example coverage is tracked per exact Hugging Face checkpoint and
task in the machine-readable
[`recipe_coverage.yaml`](https://github.com/vllm-project/vllm-omni/blob/main/docs/models/recipe_coverage.yaml).
The registry is populated as coverage is audited and is the source of truth
for mapping exact checkpoints and tasks to links. Recipe files under
[`recipes/`](https://github.com/vllm-project/vllm-omni/tree/main/recipes) remain
the source of truth for commands and validation details. It uses the following
link precedence:
1. `published`: link to the published `recipes.vllm.ai` page.
2. `repository`: link to the in-repository recipe until a published page exists.
3. `no_validated_recipe_yet`: show `No validated recipe yet` only when that
result has been explicitly audited.
4. A checkpoint/task without an entry: coverage has not been audited yet.
Split entries whenever checkpoints, tasks, examples, or validation evidence
differ. A single Supported Models row may therefore map to multiple registry
entries.
<sup>H3</sup> MiniMax H3 AMD GPU support is validated on gfx942 (MI300X) and
gfx950 (MI350) in BF16, using the AITER `FLASH_ATTN` diffusion attention backend.
Other AMD SKUs (e.g. MI325X) are not listed until their
recipes/README.md
+6
View File
@@ -19,6 +19,12 @@ 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 exact checkpoint/task mapping used by the Supported Models documentation
is tracked in
[`docs/models/recipe_coverage.yaml`](../docs/models/recipe_coverage.yaml).
This registry records link precedence; the recipe files in this directory
remain the source of truth for commands and validation details.
Example layout:
```text
tests/docs/test_generate_examples.py
+112
View File
@@ -3,8 +3,10 @@
import importlib.util
from pathlib import Path
from types import SimpleNamespace
import pytest
import yaml
pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -43,3 +45,113 @@ def test_model_display_names_require_string_mapping(tmp_path, monkeypatch):
with pytest.raises(ValueError, match="MODEL_DISPLAY_NAMES_FILE"):
generate_examples.load_model_display_names()
def test_quantization_examples_keep_source_urls_under_feature_navigation(tmp_path, monkeypatch):
nav_file = tmp_path / "docs" / ".nav.yml"
nav_file.parent.mkdir(parents=True)
nav_file.write_text(
yaml.safe_dump(
{
"nav": [
{
"User Guide": [
{
"Examples": [
"examples/README.md",
{"Offline Inference": [{"Old": "user_guide/examples/offline_inference/old.md"}]},
]
},
{"Features": [{"Quantization": [{"Overview": "user_guide/quantization/overview.md"}]}]},
]
}
]
},
sort_keys=False,
),
encoding="utf-8",
)
monkeypatch.setattr(generate_examples, "ROOT_DIR", tmp_path)
monkeypatch.setattr(generate_examples, "NAV_FILE", nav_file)
monkeypatch.setattr(generate_examples, "EXAMPLE_DOC_DIR", tmp_path / "docs/user_guide/examples")
quantization_example = SimpleNamespace(
category="quantization",
path=tmp_path / "examples/quantization/check_modelopt_fp8_export.py",
nav_title="Check Modelopt FP8 Export",
)
offline_example = SimpleNamespace(
category="offline_inference",
path=tmp_path / "examples/offline_inference/demo.py",
nav_title="Demo",
)
generate_examples.update_nav_file([quantization_example, offline_example])
generate_examples.update_nav_file([quantization_example, offline_example])
nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
user_guide = nav_data["nav"][0]["User Guide"]
examples = next(item["Examples"] for item in user_guide if "Examples" in item)
features = next(item["Features"] for item in user_guide if "Features" in item)
quantization = next(item["Quantization"] for item in features if "Quantization" in item)
assert not any(isinstance(item, dict) and "Quantization" in item for item in examples)
generated_examples = [
item[generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE]
for item in quantization
if generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE in item
]
assert len(generated_examples) == 1
assert generated_examples[0] == [
{"Check Modelopt FP8 Export": "user_guide/examples/quantization/check_modelopt_fp8_export.md"}
]
# A later build without quantization examples must not leave a stale
# generated group in the hand-authored Quantization section.
generate_examples.update_nav_file([offline_example])
nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
user_guide = nav_data["nav"][0]["User Guide"]
features = next(item["Features"] for item in user_guide if "Features" in item)
quantization = next(item["Quantization"] for item in features if "Quantization" in item)
assert not any(
isinstance(item, dict) and generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE in item
for item in quantization
)
def test_quantization_examples_are_not_added_to_examples_without_feature_target(tmp_path, monkeypatch, caplog):
nav_file = tmp_path / "docs" / ".nav.yml"
nav_file.parent.mkdir(parents=True)
nav_file.write_text(
yaml.safe_dump(
{
"nav": [
{
"User Guide": [
{"Examples": ["examples/README.md"]},
]
}
]
},
sort_keys=False,
),
encoding="utf-8",
)
monkeypatch.setattr(generate_examples, "ROOT_DIR", tmp_path)
monkeypatch.setattr(generate_examples, "NAV_FILE", nav_file)
monkeypatch.setattr(generate_examples, "EXAMPLE_DOC_DIR", tmp_path / "docs/user_guide/examples")
quantization_example = SimpleNamespace(
category="quantization",
path=tmp_path / "examples/quantization/check_modelopt_fp8_export.py",
nav_title="Check Modelopt FP8 Export",
)
generate_examples.update_nav_file([quantization_example])
nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
examples = nav_data["nav"][0]["User Guide"][0]["Examples"]
assert not any(isinstance(item, dict) and "Quantization" in item for item in examples)
assert "omitting generated quantization examples from navigation" in caplog.text
tests/docs/test_recipe_coverage.py
+142
View File
@@ -0,0 +1,142 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import re
from pathlib import Path
import pytest
import yaml
pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
ROOT_DIR = Path(__file__).parents[2]
COVERAGE_PATH = ROOT_DIR / "docs/models/recipe_coverage.yaml"
SUPPORTED_MODELS_PATH = ROOT_DIR / "docs/models/supported_models.md"
VALID_STATUSES = {"published", "repository", "no_validated_recipe_yet"}
VALID_HARDWARE = {"nvidia", "amd", "ascend", "intel"}
HARDWARE_COLUMNS = {
"nvidia": 4,
"amd": 5,
"ascend": 6,
"intel": 7,
}
def load_entries() -> list[dict]:
data = yaml.safe_load(COVERAGE_PATH.read_text(encoding="utf-8"))
assert data["version"] == 1
assert isinstance(data["entries"], list)
return data["entries"]
def supported_model_ids() -> set[str]:
model_ids = set()
for line in SUPPORTED_MODELS_PATH.read_text(encoding="utf-8").splitlines():
if not line.startswith("|"):
continue
columns = line.split("|")
if len(columns) <= 3:
continue
model_ids.update(re.findall(r"`([^`]+/[^`]+)`", columns[3]))
return model_ids
def supported_model_recipe_cells() -> dict[str, str]:
recipe_cells = {}
in_table = False
for line in SUPPORTED_MODELS_PATH.read_text(encoding="utf-8").splitlines():
if line.startswith("| Architecture |"):
in_table = True
continue
if in_table and not line.startswith("|"):
break
if not in_table:
continue
columns = line.split("|")
if len(columns) <= 8 or columns[1].strip().startswith("-"):
continue
for model_id in re.findall(r"`([^`]+/[^`]+)`", columns[3]):
recipe_cells[model_id] = columns[8].strip()
return recipe_cells
def expected_recipe_link(entry: dict) -> str:
recipe = entry["recipe"]
if recipe["status"] == "published":
return recipe["published_url"]
if recipe["status"] == "repository":
return f"https://github.com/vllm-project/vllm-omni/blob/main/{recipe['repository_path']}"
return "No validated recipe yet"
def supported_model_hardware_cells() -> dict[str, list[str]]:
hardware_cells = {}
in_table = False
for line in SUPPORTED_MODELS_PATH.read_text(encoding="utf-8").splitlines():
if line.startswith("| Architecture |"):
in_table = True
continue
if in_table and not line.startswith("|"):
break
if not in_table:
continue
columns = line.split("|")
if len(columns) <= 8 or columns[1].strip().startswith("-"):
continue
cells = [columns[index].strip() for index in HARDWARE_COLUMNS.values()]
for model_id in re.findall(r"`([^`]+/[^`]+)`", columns[3]):
hardware_cells[model_id] = cells
return hardware_cells
def test_registry_keys_are_exact_supported_checkpoints():
entries = load_entries()
keys = [(entry["model"], entry["task"]) for entry in entries]
assert len(keys) == len(set(keys))
assert all(entry["model"] in supported_model_ids() for entry in entries)
def test_supported_models_render_registry_recipe_links():
recipe_cells = supported_model_recipe_cells()
for entry in load_entries():
assert expected_recipe_link(entry) in recipe_cells[entry["model"]]
def test_registry_entries_have_explicit_recipe_precedence():
for entry in load_entries():
assert set(entry) >= {"model", "task", "examples", "recipe"}
assert isinstance(entry["examples"], list)
recipe = entry["recipe"]
status = recipe["status"]
assert status in VALID_STATUSES
assert set(recipe.get("hardware", [])) <= VALID_HARDWARE
if status == "published":
assert recipe["published_url"].startswith("https://recipes.vllm.ai/")
elif status == "repository":
assert recipe["repository_path"].startswith("recipes/")
assert "published_url" not in recipe
else:
assert "published_url" not in recipe
assert "repository_path" not in recipe
paths = [*entry["examples"], recipe.get("repository_path")]
for relative_path in filter(None, paths):
path = Path(relative_path)
assert not path.is_absolute()
assert (ROOT_DIR / path).is_file(), relative_path
def test_supported_models_render_recipe_hardware():
hardware_cells = supported_model_hardware_cells()
for entry in load_entries():
recipe_hardware = set(entry["recipe"].get("hardware", []))
cells = hardware_cells[entry["model"]]
for hardware, cell in zip(HARDWARE_COLUMNS, cells, strict=True):
assert (cell == "✅︎") == (hardware in recipe_hardware)