tzhouamandClaude Fable 5.1 82955b3a22 [Edge][CPU] Default the code predictor's CPU fast path to fp32 + compiled static step; int8 opt-in ...

In-situ parity against the bf16 model (VLLM_OMNI_PREDICTOR_PARITY_CHECK=1):
fp32 control keeps 93.8 % top-1 / 95 % top-5 / KL 0.0015; torch.ao dynamic
int8 falls to 22 % top-1 (max logit diff 7), so per-tensor activation
quantization is not acceptable as a default. Adds the ao-nohead variant
(int8 transformer body, fp32 lm heads) for measurement.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-10 02:54:53 +08:00

..

audex

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

aura_omni

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

bagel

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

common

[Edge][CPU] Default the code predictor's CPU fast path to fp32 + compiled static step; int8 opt-in

2026-09-10 02:54:53 +08:00

cosyvoice3

[Bugfix][TTS] Make CosyVoice3 TRT plan publication concurrency-safe (#6955)

2026-09-03 06:44:42 +00:00

covo_audio

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

dots_tts

[Feat][dots.tts] Add Online Serving Support (#6235)

2026-09-04 14:44:10 -07:00

dreamzero

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

dynin_omni

[Refactor][2/N Scheduler]Replace _FULL_PAYLOAD_INPUT_STAGES with a resolved stage transport capability. (#6149)

2026-08-25 15:24:59 +08:00

fish_speech

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

gepard

[Model] Add Gepard-1.0 native-AR FSQ/NanoCodec TTS (offline inference) (#5666)

2026-08-14 22:06:05 -07:00

glm_image

[Perf][GLM-Image] Skip redundant hidden state D2H (#5346)

2026-07-28 20:34:35 +08:00

glm_tts

[Perf][TTS] glm_tts: hoist loop-invariant text embed, RoPE, mask and CFG batch out of Euler loop (#5068)

2026-08-12 17:02:02 +00:00

gr00t

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

higgs_audio_v2

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

higgs_audio_v3

[Bugfix] Fix Higgs Audio v3 voice-clone token validation (#7065)

2026-09-04 16:06:47 -07:00

hunyuan_image3

[Bugfix] Fix Hunyuan Image-3 expert mapping contract (#7021)

2026-09-06 21:43:37 +08:00

hunyuan_video

[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)

2026-07-18 09:34:33 +00:00

indextts2

[Bugfix] Fix fallback loading for IndexTTS external models (#6137)

2026-09-04 19:58:33 -07:00

lance

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

lingbot_world

[Feature][LingBot World]stepwise execution (#6844)

2026-09-07 13:38:23 +08:00

mammoth_moda2

[Fix] Restore MammothModa2 support (#6694)

2026-08-28 08:32:32 +08:00

mimo_audio

[Bugfix][MiMo-Audio] Restore make_empty_intermediate_tensors on the talker for vLLM 0.28 (#6803)

2026-08-31 15:26:35 +08:00

ming_flash_omni

[Ming] Cleanup Ming-family shared modules (#6119)

2026-08-19 14:13:40 +08:00

ming_tts

[Ming] Cleanup Ming-family shared modules (#6119)

2026-08-19 14:13:40 +08:00

minicpmo_4_5

[Model] Preserve MiniCPM-o Talker full attention until capacity (#6799)

2026-09-06 22:25:35 +08:00

minimax_h3

[Model] MiniMax-H3: validate versioned text-conditioning handoff (#6720)

2026-09-06 21:45:10 +08:00

minimax_music3

[Bugfix][MiniMax-Music3] Resolve stage subdirs against a real snapshot (#6640)

2026-08-30 06:51:24 +00:00

moss_tts

[Feature][Moss-TTS] Reference Audio Preprocessing (#4982)

2026-09-04 16:36:26 -07:00

moss_tts_nano

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

nemotron_voicechat

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

omnivoice

[Perf][Bugfix][OmniVoice] Restore float16 serving, and fuse the generator hot loop (#6317)

2026-09-02 19:54:55 +00:00

personaplex

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

qwen2_5_omni

[Bugfix][Qwen2.5-Omni] Fix two stale call sites in the speech helpers (#6886)

2026-09-02 21:41:05 -07:00

qwen3_omni

[Bugfix] Give exact-shape codec models an unpadded input_ids view (#6775)

2026-09-04 15:28:49 -07:00

qwen3_tts

[Edge][CPU] KV-cached code predictor, int8-dynamic CPU fast path, model-side CPU sampler

2026-09-10 01:56:00 +08:00

step_audio2

[Bugfix][TTS] Isolate concurrent StepAudio2 TRT builds (#6957)

2026-09-02 19:53:02 +00:00

voxcpm2

[Refactor] Move model-specific capability metadata into TTS adapters (#6138)

2026-08-22 14:26:49 +08:00

voxtral_tts

[Perf][TTS] voxtral_tts hot path: cudagraph opt-out, host-sync removal, kernel caches (#5175)

2026-08-10 21:03:32 -07:00

wan2_2

[FEAT]Add FastVideo VSA backend for Wan2.2 (#4820)

2026-08-24 14:48:31 +08:00

__init__.py

[Core] Unified quantization framework (#1764)

2026-03-24 18:56:55 +08:00

output_templates.py

[Refactor] Standardize data entry key names to {type}.{qualifier} format (#1829)

2026-04-25 18:15:38 +08:00

registry.py

[model]Add experimental Mage-VL full-duplex adapter and offline integration (#6537)

2026-09-02 20:25:32 -07:00

utils.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

whisper_utils.py

[Model] Add Ming-flash-omni-2.0 Thinker Stage (#1822)

2026-04-17 19:10:02 +08:00