vllm-omni

aura_omni

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

bagel

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

common

[Model] Add Ming-omni-tts MoE 16.8B-A3B + CFM CUDAGraph (#4341 )

2026-06-25 22:11:35 +08:00

cosyvoice3

[Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496 )

2026-06-23 14:38:32 +08:00

covo_audio

[Core] Remove dead custom_process_input_func hooks in stage input processors (#4531 )

2026-06-29 05:17:25 +02:00

dreamzero

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

dynin_omni

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

fish_speech

[Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496 )

2026-06-23 14:38:32 +08:00

glm_image

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

glm_tts

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

gr00t

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

higgs_audio_v2

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

higgs_audio_v3

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

hunyuan_image3

[perf] avoid HunyuanImage3 timestep scalar sync (#4363 )

2026-06-24 11:05:35 +08:00

indextts2

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

lance

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

mammoth_moda2

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

mimo_audio

[Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496 )

2026-06-23 14:38:32 +08:00

ming_flash_omni

[Core] Remove dead custom_process_input_func hooks in stage input processors (#4531 )

2026-06-29 05:17:25 +02:00

ming_tts

[Model] Add Ming-omni-tts MoE 16.8B-A3B + CFM CUDAGraph (#4341 )

2026-06-25 22:11:35 +08:00

minicpmo_4_5

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

moss_tts

[Model] Support MOSS-TTS-local-v1.5 (#4664 )

2026-06-25 15:43:03 +08:00

moss_tts_nano

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

omnivoice

[Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496 )

2026-06-23 14:38:32 +08:00

qwen2_5_omni

Fix Qwen2.5-Omni AutoRound loading (#4781 )

2026-06-29 07:34:27 +00:00

qwen3_omni

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

qwen3_tts

[Model] Aura support - Non async chunk path (#4257 )

2026-06-21 22:08:26 +08:00

step_audio2

[Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567 )

2026-06-19 15:05:26 +08:00

voxcpm2

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760 )

2026-06-24 11:02:29 +08:00

voxtral_tts

[Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567 )

2026-06-19 15:05:26 +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] Support MOSS-TTS-local-v1.5 (#4664 )

2026-06-25 15:43:03 +08:00

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