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

[Refactor] Remove dependency on librosa (#2273)

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

chart-helm

[Feature] Add Helm Chart to deploy vLLM-Omni on Kubernetes (#1337)

2026-03-09 16:02:23 +00:00

dynin_omni

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

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

fish_speech

[Misc] Make gradio an optional dependency and upgrade to >=6.7.0 (#2221)

2026-03-28 12:33:55 -04:00

glm_image

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

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

helios

[Feature] Add a extra body param in create video api (#1955)

2026-03-24 13:02:35 +08:00

image_to_image

[Feat] image2image for Z-Image (#1580)

2026-04-08 14:41:24 +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

mimo_audio

[skip ci][Docs] Add FlashAttention requirement for audio generation to prevent noise-only outputs in mimo-audio model (#2205)

2026-03-26 10:21:00 +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

[OmniVoice] Add two-stage TTS serving support (#2463)

2026-04-03 20:41:20 +00:00

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

[Qwen3-TTS] Remove hardcoded distributed_executor_backend to improve single-GPU performance (#2604)

2026-04-14 14:49:13 +08:00

text_to_image

[HunyuanImage3] Align system_prompt support with official implementation (#2270)

2026-04-07 15:37:17 +08:00

text_to_video

[Doc] Add LTX-2 online serving deployment recipes with optimization benchmarks (#1971)

2026-04-11 16:50:03 +08:00

voxcpm2

[Fix] VoxCPM2: support raw audio for voice cloning via OpenAI API (#2720)

2026-04-13 06:30:56 +00:00

voxtral_tts

[Misc] Make gradio an optional dependency and upgrade to >=6.7.0 (#2221)

2026-03-28 12:33:55 -04:00

openai_chat_completion_client_for_multimodal_generation.py

[Bugfix] remove default sampling parameters (#2173)

2026-03-25 20:34:13 -07:00