3 people e04210d690 [Hardware][MUSA] Enable Qwen3-Omni ModelOpt FP8 inference (#5671) ...

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-08-11 17:19:09 +08:00

..

audex

[New Model] support nemotron Audex (#4976)

2026-07-28 03:58:22 +00:00

aura_omni

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

bagel

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

common

[CI failed] Revert "[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor" (#5777)

2026-08-04 15:21:38 +00:00

cosyvoice3

[Perf][MiniCPM-O-4.5]Add CUDA Graph For HiFTGenerator (#5869)

2026-08-09 22:29:49 +08:00

covo_audio

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

dreamzero

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

dynin_omni

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

fish_speech

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

glm_image

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

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

glm_tts

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +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][Higgs-Audio-V3] Propagate Sampling Parameters to Sampler (#5406)

2026-07-25 15:25:35 +00:00

hunyuan_image3

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

hunyuan_video

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

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

indextts2

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

lance

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

mammoth_moda2

[Model] Support MammothModa2-Dev (#5411)

2026-07-27 17:01:54 +08:00

mimo_audio

[Bugfix][Perf] mimo_audio: fix per-request speech-code routing under continuous batching (#5070)

2026-07-20 17:22:45 +00:00

ming_flash_omni

[Perf][Ming-TTS] Cache speaker embeddings for uploaded reference audio (#5240)

2026-07-23 11:22:51 +08:00

ming_tts

[Bufix] Ming-omni-tts-16.8B Skip rejected and unused weights loading (#5607)

2026-07-30 22:38:40 +08:00

minicpmo_4_5

[Model] Batch MiniCPM-o Talker codec sampling (#5792)

2026-08-11 14:05:02 +08:00

moss_tts

[BugFix] Fix MOSS-TTS codec v1/v2 detection and align vendored tokenizer with upstream (#5635)

2026-08-05 08:24:32 +00:00

moss_tts_nano

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

omnivoice

[Config] Return VllmOmniConfig from create_from_model (#4818)

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

personaplex

[Feature] PersonaPlex (Moshi-based full-duplex S2S): native vLLM port + duplex serving (#4771)

2026-08-04 20:10:33 -07:00

qwen2_5_omni

[Quantization][Qwen2.5-Omni] Support thinker-only ModelOpt NVFP4 W4A4 checkpoints (#5073)

2026-08-09 02:45:57 +08:00

qwen3_omni

[Hardware][MUSA] Enable Qwen3-Omni ModelOpt FP8 inference (#5671)

2026-08-11 17:19:09 +08:00

qwen3_tts

[Perf][Qwen3-TTS]Cached Incremental Decode (#5202)

2026-08-11 05:24:04 +00:00

soulx_singer

[BugFix] Fix SoulX-Singer deploy pipeline registration (#5210)

2026-07-20 14:34:42 +00:00

step_audio2

[Perf][TTS] step_audio2: keep streaming tokens on-device and batch audio-feature length syncs (#5067)

2026-08-10 21:24:25 -07:00

voxcpm2

[Bugfix][VoxCPM2] Fix Chunked Prefill Length Mismatch (#5416)

2026-07-31 05:44:53 +00:00

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

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

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

__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

[Feature] PersonaPlex (Moshi-based full-duplex S2S): native vLLM port + duplex serving (#4771)

2026-08-04 20:10:33 -07:00

utils.py

[Rebase] Rebase to vllm 0.23.0 (#4286)

2026-06-13 16:43:02 +00:00

whisper_utils.py

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

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