Yueqian Lin fc81b8504a feat(moss-tts-nano): add online serving, Gradio demo, and fix /v1/audio/speech integration ...

- Register moss_tts_nano as TTS model stage in serving_speech.py
  (model detection, validation, prompt building)
- Fix registry mod_relname: moss_tts_nano -> modeling_moss_tts_nano
- Fix stage config: is_comprehension=true (required for generate task)
- Fix default mode: voice_clone -> continuation (built-in presets)
- Add compute_logits stub for VllmModelForTextGeneration protocol
- Remove unused _sentinel nn.Parameter
- Add Gradio demo with AudioWorklet streaming player (48kHz stereo)
- Add online/offline serving docs and launch scripts

TODO: Single-stage generation models don't support true streaming
(progressive audio chunks). Current TTFP = full generation time.
Needs multi-step scheduling support in GPUGenerationModelRunner.

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>

2026-04-14 13:06:44 -04:00

..

bagel

[Bagel]: Support think mode in single stage deployment of Bagel (#2650)

2026-04-13 11:15:49 +00:00

cosyvoice3

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

custom_pipeline/image_to_image

[Entrypoint][Refactor] vLLM-Omni Entrypoint Refactoring (#1908)

2026-03-18 17:33:53 +08:00

dynin_omni

[Model] Add Dynin-omni model in vllm-omni (#1759)

2026-04-09 16:37:34 +08:00

fish_speech

[Bugfix] Fix Fish Speech voice clone FileNotFoundError on multi-GPU (#2606)

2026-04-09 20:34:34 +00:00

glm_image

[Doc] Add transformers version requirement in GLM-Image example doc (#2265)

2026-03-29 15:56:51 +00:00

helios

[Feat] add helios fp8 quantization (#1916)

2026-03-29 06:35:56 +00:00

hunyuan_image3

[BugFIX] enable Hunyuan image3 with stage selection among text_to_image/image_to_text (#1826)

2026-03-24 13:00:21 +08:00

image_to_image

[Refactor] Extend CFG Parallel to support 3 or 4 branch dispatch across M GPUs (#2423)

2026-04-12 22:06:49 +08:00

image_to_video

[Model] Adapt Wan2.2-I2V-A14B via LightX2V offline conversion path (#2134)

2026-04-13 14:20:04 +08:00

magi_human

[MagiHuman] Fix audio sample rate and fps propagation for online serving (#2554)

2026-04-09 06:52:12 +00:00

mammothmodal2_preview

[Performance] diffusion timing (#1757)

2026-03-19 12:26:12 +08:00

mimo_audio

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

moss_tts_nano

feat(moss-tts-nano): add online serving, Gradio demo, and fix /v1/audio/speech integration

2026-04-14 13:06:44 -04:00

omnivoice

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

qwen2_5_omni

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

qwen3_omni

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

qwen3_tts

[Misc] Clean up unused diffusion timing args in examples (#2266)

2026-03-28 07:03:17 +08:00

text_to_audio

[Test] Add Stable Audio offline e2e TeaCache Test (#2377)

2026-04-14 15:05:12 +08:00

text_to_image

[Bugfix] Restore user config/runtime stage init timeout (#2519)

2026-04-12 00:48:47 +08:00

text_to_video

[MagiHuman] Fix audio sample rate and fps propagation for online serving (#2554)

2026-04-09 06:52:12 +00:00

vace

Add VACE support for WAN 2.1 conditional video generation (#1885)

2026-04-02 15:42:50 +08:00

voxcpm2

[Perf]: Speedup VoxCPM2 TTS performance and Support PagedAttention (#2690)

2026-04-14 09:16:47 +12:00

voxtral_tts

[Voxtral TTS] Add multilingual support in gradio demo (#2151)

2026-03-25 01:20:32 +00:00

x_to_video_audio

[Refactor] Extend CFG Parallel to support 3 or 4 branch dispatch across M GPUs (#2423)

2026-04-12 22:06:49 +08:00