anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,271 Commits 235 Branches 31 Tags
033e4041bebcf4c7d1e4363867ce6bc438fa2e1f
Commit Graph
1271 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Yueqian Lin 033e4041be fix(moss-tts-nano): remove unused voice variable (ruff F841) 
The upstream inference_stream() API has no voice/spk parameter;
voice preset selection is not yet wired into the call. Remove the
dead assignment to silence ruff F841.

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:11:43 -04:00
Yueqian Lin 38aaaebeda feat(moss-tts-nano): enable progressive streaming via AR runner 
Switch from GPUGenerationWorker to AR worker with OmniARScheduler,
using the VoxCPM-style generator pattern for streaming:

- inference_stream() stored per-request in _stream_gens dict
- Each forward() call yields one audio chunk via next(generator)
- compute_logits() emits EOS only when last chunk is yielded
- AR scheduler loops until EOS, enabling progressive audio output

TTFP reduced from ~3.1s to ~0.11s (30x improvement).

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:06:44 -04:00
Yueqian Lin 71db0c5ef5 fix(moss-tts-nano): add buildkite pre-merge test, remove misplaced docs 
- Add MOSS-TTS-Nano E2E test to .buildkite/test-merge.yml
- Remove docs from docs/ (will be synced from examples/ READMEs)

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:06:44 -04:00
Yueqian Lin 45e8829f07 docs(moss-tts-nano): add e2e online serving test and user guide docs 
- Add online serving e2e test (non-streaming, streaming, Chinese)
- Add online serving user guide doc (API, voices, Gradio, curl/Python)
- Add offline inference user guide doc

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:06:44 -04:00
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
Yueqian Lin 571c8d4235 fix(moss-tts-nano): also patch torchaudio.save for soundfile fallback 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:06:12 -04:00
Yueqian Lin 0b8190d07f fix(moss-tts-nano): patch torchaudio.load to use soundfile when torchcodec unavailable 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:06:12 -04:00
Yueqian Lin da6b1b5741 feat(moss-tts-nano): add single-stage MOSS-TTS-Nano TTS support 
Integrates OpenMOSS-Team/MOSS-TTS-Nano (0.1B) as a single
GPUGenerationWorker stage.  Both the AR LM and MOSS-Audio-Tokenizer-Nano
codec run inside MossTTSNanoForGeneration.forward(), removing the need for
an inter-stage connector.

Key design choices:
- Weights loaded in load_weights() not __init__ (avoids pre-CUDA alloc)
- trust_remote_code delegates to upstream HF model classes
- codec path read from config.audio_tokenizer_pretrained_name_or_path
- inference_stream() collects progressive audio chunks for low latency
- 48 kHz stereo output; voice clone + continuation modes supported


Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-14 13:06:12 -04:00
Yiyang "Ian" LiuandSYLAR bc4a659f03 [Bugfix] Make mrope kwargs optional in HunyuanImage3 get_mrope_input_positions (#2654) 
Signed-off-by: Yiyang Liu <yiyangliu@microsoft.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-04-14 14:41:28 +00:00
amy-why-3459 f03ab38783 [BugFix] Fix NoneType' object has no attribute 'detach' (#2797) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-14 10:26:55 -04:00
Yiyang "Ian" LiuandCopilot 53a9cf49a6 fix: do not apply FP8 quant config to vision/audio encoders for pre-quantized checkpoints (#2702) 
Signed-off-by: Yiyang Liu <37043548+ianliuy@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
 2026-04-14 13:52:32 +00:00
Bvicii 4fb078a031 [Bugfix] Reject /v1/audio/speech for Qwen omni models (#2763) 
Signed-off-by: Bvicii <yizhanhuang2002@gmail.com>
 2026-04-14 12:53:06 +00:00
Alex Brooks cf1fcd5acf [CI/BugFix] Fix Flaky Test for Qwen Omni Perf (#2754) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
 2026-04-14 20:49:57 +08:00
wangyu 5ce0a43492 [CI][Bugfix] Update thresholds for accuracy tests (#2725) 
Signed-off-by: wangyu <410167048@qq.com>
 2026-04-14 20:48:04 +08:00
n1ptuneandneptune bcd5f16321 [Misc] clean Temporary CI Configs (#2784) 
Signed-off-by: neptune <neptune@hust.edu.cn>
Co-authored-by: neptune <neptune@hust.edu.cn>
 2026-04-14 12:41:23 +00:00
Hongsheng Liu f87674aa44 [skip ci]add skills (#2710) 
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
 2026-04-14 20:26:27 +08:00
amy-why-3459 159d6558ea [Tests][Qwen3-Omni]Add test cases for long videos and long audios. (#2598) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-14 19:36:02 +08:00
rongfu.leng 3229bae331 [skip ci] fix docs, gdown remove --id param (#2787) 
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
 2026-04-14 18:33:31 +08:00
NATURE 6d01a8b506 [Omni Connector] Omni Transfer Engine Connector: Enable 1-receiver-to-N-senders to support Bagel TP/CFG parallel (#2731) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
 2026-04-14 16:06:37 +08:00
Zhang JianandClaude Opus 4.6 17acd0589a [Test] Add Stable Audio offline e2e TeaCache Test (#2377) 
Signed-off-by: Zhang <jianmusings@gmail.com>
Signed-off-by: Zhang Jian <jianmusings@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-14 15:05:12 +08:00
iancarrasco-b10 48c30bc399 [Qwen3-TTS] Remove hardcoded distributed_executor_backend to improve single-GPU performance (#2604) 
Signed-off-by: Ian Carrasco <ian.carrasco@baseten.co>
 2026-04-14 14:49:13 +08:00
Samit 644edac0b6 [Perf] Optimize MP4 encoding latency in video generation (#2735) 
Signed-off-by: samithuang <285365963@qq.com>
 2026-04-14 14:20:38 +08:00
amy-why-3459 a5b38b5d0d [BugFix] Remove stage_configs_path validation (#2741) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-14 17:32:00 +12:00
Zeyu Huang | 黃澤宇 8d23549b29 [CI] Qwen image edit performance benckmark (#2216) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
 2026-04-14 11:35:56 +08:00
Chen-Yo Sun dd1389173b [Voxtral TTS] Fix Voxtral TTS input with text and ref_audio (#2750) 
Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
 2026-04-13 22:37:45 +00:00
Sy03Yueqian LinYueqian Lin
 		14f7910900 [Perf]: Speedup VoxCPM2 TTS performance and Support PagedAttention (#2690) 
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-04-14 09:16:47 +12:00
Chen-Yo Sun c9e2e3e8d7 [Voxtral TTS] Correct decode steps param in Voxtral TTS (#2524) 
Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
 2026-04-13 17:53:35 +00:00
Didan Deng 6b5a52ae31 [Bugfix] Update Flux2-dev & Dynin_omni L4 e2e test (#2723) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-04-13 20:50:38 +08:00
amy-why-3459 2a1d5060ab [skip ci][doc]Update async_chunk design diagram (#2420) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-13 20:43:40 +08:00
Yuanheng Zhao e0cdbe9a5d [Misc] Cleanup: use consistent pytest-mock in unit tests (#2698) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
 2026-04-13 19:21:42 +08:00
汪志鹏 2c67c30550 [Bagel]: Support think mode in single stage deployment of Bagel (#2650) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-04-13 11:15:49 +00:00
amy-why-3459 ef3f72b9ae [Tests][Qwen3-Omni]Modify Qwen3-Omni performance test cases (#2600) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-13 19:03:13 +08:00
Chenguang Zheng 155583f49f [Bugfix] Release stage launch lock before handshake (#2717) 
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
 2026-04-13 18:35:59 +08:00
JohnJanandwuzhongjian cd2761e15c [Feature]: support Flux.2-dev tea_cache (#1871) 
Co-authored-by: wuzhongjian <wuzhongjian@cmss.chinamobile.com>
 2026-04-13 17:51:48 +08:00
NATUREandHongsheng Liu 0d4e975e1b [core]refactor communication layer: PR1(Added Refactor Infra Only) (#1555) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-13 16:01:14 +08:00
amy-why-3459 2b70e89535 [Revert] Revert "[Log] Wire stat loggers into AsyncOmniEngine to match AsyncLL… (#2716) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-13 14:55:16 +08:00
wangyu 22261430b4 [CI][Bugfix] Refactor the test case to add support for increasing init timeout and stage init timeout in order to resolve the CI timeout error. (#2711) 
Signed-off-by: wangyu <410167048@qq.com>
 2026-04-13 14:47:55 +08:00
Yueqian Lin d9e745ce2c [Fix] VoxCPM2: support raw audio for voice cloning via OpenAI API (#2720) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-13 06:30:56 +00:00
Jiaqian LiuandCanlin Guo 8097747a5d [Model] Adapt Wan2.2-I2V-A14B via LightX2V offline conversion path (#2134) 
Signed-off-by: Celeste-jq <591998922@qq.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-04-13 14:20:04 +08:00
Sy03 cb4d13a658 [Perf][Fish Speech] Enable CUDA Graph capture for Fast AR code predictor (#2520) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-04-13 04:53:35 +00:00
NATURE e12250119b [Bugfix] Fix Bagel online mode for 1. Hang after several requests 2. Non-deterministic image quality regression. (#2458) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
 2026-04-13 03:36:20 +00:00
Zhengyuan Su (苏政渊)andClaude Opus 4.6 eb1a801b21 [Feat] Override single stage CLI args when stage_configs_path is set in OmniEngineArgs (#2684) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 11:08:52 +08:00
TJian 2dce028541 [ROCm] [CI] Fix environment issue (#2708) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2026-04-12 15:37:17 +00:00
Canlin Guo 95b5b2ee43 [Bugfix] Fix UT for the missing of log_stats in Engine (#2706) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-04-12 22:14:43 +08:00
zhou zhuoxin 16041ab550 [Refactor] Extend CFG Parallel to support 3 or 4 branch dispatch across M GPUs (#2423) 2026-04-12 22:06:49 +08:00
Alex BrooksandSYLAR ef230ac720 [Bugfix] Fix Incompatible Multihook Integration (TeaCache <-> CPU Offload) (#2689) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-04-12 21:44:06 +08:00
Canlin Guo 5d58abb11e [Log] Wire stat loggers into AsyncOmniEngine to match AsyncLLM (#2551) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-04-12 19:54:23 +08:00
WeiQing Chenanddavid6666666 73fb68ad28 [Docs] Update WeChat QR code for community support (#2701) 
Signed-off-by: david6666666 <david6666666@users.noreply.github.com>
Co-authored-by: david6666666 <david6666666@users.noreply.github.com>
 2026-04-12 04:42:44 +00:00
ReidandHongsheng Liu 38dfe56fdf [Bugfix] Validate speaker in chat endpoint and fix case-insensitive lookup (#2407) 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-12 00:14:16 -04:00
Yuanheng ZhaoHongsheng LiuSYLAR
 		c20cac86ce [Bugfix] Restore user config/runtime stage init timeout (#2519) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-04-12 00:48:47 +08:00