Sy03andYueqian Lin 3bc3f1a7d0 [Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213) ...

Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>

2026-10-02 18:03:14 +00:00

..

__init__.py

[Model] Add YuE2-3B text-to-music (model + /v1/audio/speech adapter) (#7886)

2026-10-01 18:04:31 +08:00

audex_tta.py

[Migrate]Move model-specific helpers out of serving_speech (#6697)

2026-09-08 08:59:45 +08:00

audex.py

[Core] Retain structured configs through runtime startup (#6849)

2026-09-16 20:47:38 -07:00

audio8_tts.py

[Bugfix][TTS] Fix Audio8 voice clone reference resolution (#7815)

2026-09-21 19:13:03 -07:00

auk.py

[Feat][Perf][AuK]Support Online Serving and DiT CUDAGraph (#7469)

2026-09-30 00:18:38 +00:00

base.py

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213)

2026-10-02 18:03:14 +00:00

breeze_tts_2.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752)

2026-09-22 17:10:15 -07:00

capabilities.py

[Bugfix] Replace hardcoded Vivian speaker default with config-ordered default (#5814)

2026-09-24 09:10:01 -07:00

cosyvoice3.py

[Model] Add opt-in packed Flow and batched HiFT inference for CosyVoice3 (#8224)

2026-09-29 15:48:36 +00:00

covo_audio.py

[Migrate]Move model-specific helpers out of serving_speech (#6697)

2026-09-08 08:59:45 +08:00

fish_speech.py

[Migrate]Move model-specific helpers out of serving_speech (#6697)

2026-09-08 08:59:45 +08:00

gepard.py

[Model] Add Gepard-1.0 OpenAI /v1/audio/speech serving (#7499)

2026-09-15 14:56:51 -07:00

glm_tts.py

[Bugfix] Replace hardcoded Vivian speaker default with config-ordered default (#5814)

2026-09-24 09:10:01 -07:00

higgs_audio_v2.py

[Bugfix]Include Reference Audio Cache Salt for HiggsAudio v2 (#7826)

2026-09-20 00:19:14 +08:00

higgs_audio_v3.py

[Core] Retain structured configs through runtime startup (#6849)

2026-09-16 20:47:38 -07:00

indextts2.py

[Bugfix] Invalidate stale ref_audio cache on local file modification (#4873) (#5670)

2026-08-25 10:06:32 +08:00

ming_flash_omni_tts.py

[Bugfix] Replace hardcoded Vivian speaker default with config-ordered default (#5814)

2026-09-24 09:10:01 -07:00

ming_tts.py

[Bugfix] Replace hardcoded Vivian speaker default with config-ordered default (#5814)

2026-09-24 09:10:01 -07:00

minimax_music3.py

[Model] Add MiniMax Music 3 text-to-music (#6186)

2026-08-18 04:33:13 +00:00

moss_tts.py

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213)

2026-10-02 18:03:14 +00:00

omnivoice.py

[Bugfix] Invalidate stale ref_audio cache on local file modification (#4873) (#5670)

2026-08-25 10:06:32 +08:00

qwen3_tts.py

[Model] Add single-stage Qwen3-TTS with in-Talker streaming codec decode (#8259)

2026-10-02 21:34:30 +10:00

step_audio2.py

[Migrate]Move model-specific helpers out of serving_speech (#6697)

2026-09-08 08:59:45 +08:00

voxcpm2.py

[Bugfix] Replace hardcoded Vivian speaker default with config-ordered default (#5814)

2026-09-24 09:10:01 -07:00

voxtral.py

[Bugfix] Replace hardcoded Vivian speaker default with config-ordered default (#5814)

2026-09-24 09:10:01 -07:00

yue2.py

[Model] YuE2: async single-stage synthesis and CUDA graph acceleration (#8407)

2026-10-02 05:17:06 -07:00