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

..

assets

[Refactor] Remove dependency on librosa (#2273)

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

benchmarks

[CI/BugFix] Fix Flaky Test for Qwen Omni Perf (#2754)

2026-04-14 20:49:57 +08:00

config

[Core] Unified quantization framework (#1764)

2026-03-24 18:56:55 +08:00

core

[core]refactor communication layer: PR1(Added Refactor Infra Only) (#1555)

2026-04-13 16:01:14 +08:00

diffusion

[Perf] Optimize MP4 encoding latency in video generation (#2735)

2026-04-14 14:20:38 +08:00

distributed

[Omni Connector] Omni Transfer Engine Connector: Enable 1-receiver-to-N-senders to support Bagel TP/CFG parallel (#2731)

2026-04-14 16:06:37 +08:00

engine

[BugFix] Remove stage_configs_path validation (#2741)

2026-04-14 17:32:00 +12:00

entrypoints

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

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

inputs

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

2026-04-08 14:41:24 +08:00

lora

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

metrics

Revert "[Profile] Adding metrics for Diffusion/DiT Single diffusion Pipeline (#668)" (#1724)

2026-03-08 00:11:47 +13:00

model_executor

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

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

platforms

[Bugfix] Fix Bagel online mode for 1. Hang after several requests 2. Non-deterministic image quality regression. (#2458)

2026-04-13 03:36:20 +00:00

plugins

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

profiler

[Feat] Add MUSA platform support for Moore Threads GPUs (#2337)

2026-04-01 17:55:00 +08:00

quantization

fix: do not apply FP8 quant config to vision/audio encoders for pre-quantized checkpoints (#2702)

2026-04-14 13:52:32 +00:00

sample

update dirs

2025-09-11 15:43:43 +08:00

tokenizers

add support for MammothModa2 model (#336)

2026-03-04 22:52:56 +08:00

transformers_utils

[Model] VoxCPM2 native AR TTS support (#2658)

2026-04-11 10:21:26 +08:00

utils

[Refactor] Remove dependency on librosa (#2273)

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

worker

[BugFix] Fix NoneType' object has no attribute 'detach' (#2797)

2026-04-14 10:26:55 -04:00

__init__.py

[Bug] Lazy-import entrypoints to fix subprocess pynvml crash (#2187)

2026-04-09 15:35:22 +08:00

logger.py

[BugFix] Failed to print DEBUG level log (#307)

2025-12-15 07:13:36 +00:00

outputs.py

[core]refactor communication layer: PR1(Added Refactor Infra Only) (#1555)

2026-04-13 16:01:14 +08:00

patch.py

[Rebase] Rebase to vllm v0.19.0 (#2475)

2026-04-04 15:03:32 +08:00

request.py

Dev/rebase v0170 (#1639)

2026-03-09 17:29:38 +08:00

version.py

[Version] Auto generate version using setuptool_scm (#1224)

2026-02-27 14:34:27 +08:00