vllm-omni

0 Fork 0

Files

T

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

layers

Update MRoPE config fallback logic (#2278 )

2026-04-02 16:28:53 +00:00

model_loader

[Fix]Ensure HuggingFace downloads complete before initialization. (#1213 )

2026-02-10 16:05:12 +08:00

models

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

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

stage_configs

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