anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,461 Commits 235 Branches 31 Tags
01ebc0cdf542bb46db90ca8ecb641f26ca9247a0
Commit Graph
55 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Yueqian Lin b1ff695029 [Bugfix][CI] Vendor Qwen3-TTS and CosyVoice3 reference audio fixtures (#3267) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-30 08:44:05 +08:00
Yueqian LinandHongsheng Liu afa2b09684 feat: add MOSS-TTS-Nano single-stage TTS support (#2753) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-27 10:26:26 +08:00
Yueqian Lin 39e3fd3d12 [Benchmark] Universal TTS benchmark: Qwen3-TTS + VoxCPM2 with 3 task types (voice-clone/default/design) (#2835) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-04-24 23:35:33 +08:00
Yueqian Lin e8d22d4fa8 docs: update add-tts-model skill and contributing guide with single-stage patterns (#2806) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-04-24 19:56:32 +08:00
Yueqian LinandSYLAR 3f504b45d2 [Config Refactor] Migrate 5 TTS models (VoxCPM2 / CosyVoice3 / MiMo Audio / Voxtral TTS / Fish Speech S2 Pro) to Pipeline + Deploy schema (#2958) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-04-21 21:17:53 +08:00
Yueqian Lin 02e5dc747d [Perf] VoxCPM2: streaming VAE + compile optimization (45% RTF reduction) (#2758) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-04-15 09:58:25 +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
Yueqian LinandSYLAR a41174e083 [Model] VoxCPM2 native AR TTS support (#2658) 
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: SYLAR <lishunyang12@users.noreply.github.com>
 2026-04-11 10:21:26 +08:00
Yueqian Lin 94232436bb [Feat][FishSpeech] Cache DAC-encoded ref audio for voice cloning (#2609) 
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-04-10 10:34:03 +08:00
Yueqian Lin 0824edefd5 ci: remove CosyVoice3 post-merge test (#2492) 2026-04-05 15:05:52 +08:00
Yueqian Lin d92439c155 [CosyVoice3] Fix vLLM 0.19.0 compatibility issues (#2486) 2026-04-05 08:45:49 +08:00
Yueqian Lin 0cf38197a0 [CI] Fix missing queue for Voxtral-TTS E2E test step (#2484) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-04-04 17:00:05 +00:00
Yueqian Lin 4c031580cf [CosyVoice3] Add online serving support, fix stage config, and add CI tests (#2431) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-04-04 14:55:15 +13:00
Yueqian Lin 0e83ebe1d4 [OmniVoice] Add two-stage TTS serving support (#2463) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-04-03 20:41:20 +00:00
Yueqian Lin 1734c1ec23 [Test] Fix 4 broken Qwen3-TTS async chunk unit tests (#2351) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-31 00:45:13 -04:00
Yueqian Lin f55ea28005 [Qwen3TTS][Bugfix] Replace vLLM fused layers with HF-compatible numerics in code predictor (#2277) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-28 10:47:17 +08:00
Yueqian Lin 9857ed2839 [Bugfix] Fix Voxtral TTS voice embeddings not loading (#2156) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-26 21:34:31 +08:00
Yueqian Lin 18d2d082aa Revert "[Test] Add Qwen-tts test cases and unify the style of existing test cases" (#2192) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-26 00:10:16 +08:00
Yueqian LinandCanlin Guo 91a818629c [Cleanup] Remove stray test file from engine directory (#2161) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-03-25 08:26:38 +00:00
Yueqian Lin 7f112041da [Bugfix] Fix high TTFP for Base task in Gradio TTS demo (#2116) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-24 22:47:09 +08:00
Yueqian Lin 4ac25287fd Add tool to configure gpu_memory_utilization for multi-stage pipelines (#1958) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-24 12:55:26 +08:00
Yueqian Lin 8b102bdac1 [Feat][Qwen3-TTS] Better Qwen3-TTS online serving demo (#1857) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-24 12:06:41 +08:00
Yueqian Lin 15f9d60dd4 [Bugfix] Fix Fish Speech and CosyVoice3 online serving - missing is_comprehension and broken model detection (#2058) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-21 22:18:10 +08:00
Yueqian Lin fe786f1a19 Fix Base voice clone streaming quality and stop-token crash (#1945) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-18 06:54:12 +08:00
Yueqian Lin cebf78ba3e [Bugfix] Restore voice upload API and profiler endpoints reverted by #1719 (#1879) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-14 04:37:08 +13:00
Yueqian Lin 366b3368ea Add Fish Speech S2 Pro support with online serving and voice cloning (#1798) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-12 16:20:52 -04:00
Yueqian Lin 9c6fbd76be Enable async_scheduling by default for Qwen3-TTS (#1853) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-12 12:30:20 -04:00
Yueqian Lin e1efcb7560 Fix duplicate get_supported_tasks definition in async_omni.py (#1825) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-11 19:43:37 -04:00
Yueqian Lin acde431668 Add Qwen3-TTS benchmark scripts (#1573) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-12 01:09:26 +08:00
Yueqian Lin f144f5effe [Test] Add Qwen3-TTS nightly performance benchmark (#1700) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-12 01:07:47 +08:00
Yueqian Lin a6b5519616 [Bugfix] Report supported tasks for omni models to skip unnecessary chat init (#1645) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-12 01:06:20 +08:00
Yueqian Lin 4db10d6dec Disable mm processor cache in CI stage configs (#1739) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-09 15:42:15 +08:00
Yueqian LinandHongsheng Liu 16248e97ef Pre-download Qwen3-TTS model in CI to avoid intermittent download timeouts (#1727) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-03-09 15:12:45 +13:00
Yueqian Lin a9f694b08a [Bugfix] Use upstream MediaConnector for ref_audio resolution (#1661) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-09 01:38:26 +00:00
Yueqian Lin 411fe05bd4 [skip CI][Docs] Add TTS model developer guide (#1693) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-06 14:49:19 +08:00
Yueqian Lin 3bc89de0c0 Add non-async chunk support for Qwen3-TTS (#1678) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-06 14:45:32 +08:00
Yueqian Lin 8536dce759 [Cleanup] Move cosyvoice3 tests to model subdirectory (#1666) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-05 15:28:22 -05:00
Yueqian Lin 35bd3ff7d2 [Bugfix] Add TTS request validation to prevent engine crashes (#1641) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-04 14:27:02 +08:00
Yueqian Lin a3240fd484 [Bugfix] Fix transformers 5.x compat issues in online TTS serving (#1536) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-03-04 01:28:32 +08:00
Yueqian Lin 37775ffe60 fix(qwen3-tts): fix Base ICL voice clone producing corrupted audio (#1554) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-02-28 11:49:47 +08:00
Yueqian Lin 5fb7d137c7 [Bugfix][Qwen3-TTS] Preserve original model ID in omni_snapshot_download (#1318) 2026-02-11 18:24:45 +08:00
Yueqian Lin f55ce9c793 [Test] Add e2e tests for Qwen3-TTS speech endpoint (#1206) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-02-10 16:33:39 +08:00
Yueqian LinandHongsheng Liu acfe99e4d9 [Doc] Update Qwen3-TTS docs for consistency with Omni examples (#1226) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-02-10 15:52:44 +08:00
Yueqian Lin accf334112 [bugfix] Fix multimodal_output property to check completion outputs where audio data is attached (#1203) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-02-08 00:39:09 +08:00
Yueqian Lin 53a44c56fe [Bugfix] Fix padding bug in 12Hz tokenizer ConvTranspose1d decode (#1241) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-02-08 00:35:49 +08:00
Yueqian Lin cac6504adf [bugfix] remove vllm speech route (#1060) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-01-29 16:02:59 +08:00
Yueqian Lin 9bca8880fe Fix TTS speaker typo and add supported languages (#990) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-01-27 23:19:51 +08:00
Yueqian Lin 77ff875170 Support Qwen3 tts online serving (#968) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-01-27 14:37:21 +08:00
Yueqian LinandHongsheng Liu 3fb6adc40a [bugfix] use unipc scheduler for Wan 2.2 (#804) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-16 12:31:25 +00:00
Yueqian Lin aaea77a180 [bugfix] Fix Wan2.2 I2V warmup failure by adding support_image_input attribute (#791) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-01-15 13:14:34 +00:00
Yueqian LinandHongsheng Liu 0cb7ec62da [Model] Add Stable Audio Open support for text-to-audio generation (#331) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-07 17:01:06 +08:00
Yueqian Lin c9a4683a1a [Bugfix] Fix TI2V-5B weight loading by loading transformer config from model (#633) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-01-05 20:39:31 +08:00
Yueqian LinandHongsheng Liu 3ec35e5409 [Model] Add Wan2.2 I2V and TI2V pipeline support (#329) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-25 16:45:13 +08:00
Yueqian Lin 4128d63c51 [Model] Add Wan2.2 text-to-video support (#202) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2025-12-11 10:38:05 +08:00
Yueqian Lin 1406c6ec71 [Misc] Add stage config for Qwen3-Omni-30B-A3B-Thinking (#172) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2025-12-04 08:41:58 -08:00