anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,775 Commits 235 Branches 31 Tags
c69ed4037dcbae7306cba9094cb42bf94de464f0
Commit Graph
1169 Commits
Author SHA1 Message Date
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
Haco 0c46ba57aa [Bugfix] restore legacy stage config precedence (#2663) 
Signed-off-by: xiaohajiayou <923390377@qq.com>
 2026-04-10 10:24:35 +08:00
Sy03 694be6f2e1 [Bugfix] Fix Fish Speech voice clone FileNotFoundError on multi-GPU (#2606) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-04-09 20:34:34 +00:00
WeiQing Chen 85d63c47f9 [Bugfix] Fix Qwen-Image min-size normalization for tiny requests (#2637) 
Signed-off-by: David Chen <530634352@qq.com>
 2026-04-09 20:51:01 +08:00
Samit 956f53b278 [Refactor] Use trajectory_* fields for Qwen-Image structured RL outputs (#2513) 
Signed-off-by: samithuang <285365963@qq.com>
 2026-04-09 03:06:40 -07:00
Ziming Huang d2aa9cf08a Revert "[Fix] Fix slow hasattr in CUDAGraphWrapper.__getattr__ (#1982)" (#2639) 
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
 2026-04-09 17:19:58 +08:00
Haco汪志鹏SYLAR
 		2d980133fe [Bugfix] Fix precedence between caller runtime args and default stage configs (#2076) 
Signed-off-by: xiaohajiayou <923390377@qq.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-04-09 16:44:31 +08:00
Dogeun KimYejoon Leeaidas
 		e2b0ee4b87 [Model] Add Dynin-omni model in vllm-omni (#1759) 
Signed-off-by: kdg6245@snu.ac.kr <kdg6245@snu.ac.kr>
Signed-off-by: Yejoon Lee (IPAI) <leeyejoon@snu.ac.kr>
Signed-off-by: aidas (arpa-kt) <aidaslab@gmail.com>
Signed-off-by: Dogeun Kim <82812668+DOGEUNNKIM@users.noreply.github.com>
Co-authored-by: Yejoon Lee (IPAI) <leeyejoon@snu.ac.kr>
Co-authored-by: aidas (arpa-kt) <aidaslab@gmail.com>
 2026-04-09 16:37:34 +08:00
LiBai 9225039d17 [Bug] Lazy-import entrypoints to fix subprocess pynvml crash (#2187) 
Signed-off-by: Meng Jianwen <mengjianwen@liblib.ai>
 2026-04-09 15:35:22 +08:00
Ting FU 0e8e630c5b [Feat] /v1/images/generations api supports request cancel (#2621) 
Signed-off-by: Semmer <semmer@live.cn>
 2026-04-09 07:08:08 +00:00
Zhengyuan Su (苏政渊)andClaude Opus 4.6 92c788e5fd [Misc] Clean up method name in BAGEL. (#2501) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-09 14:55:15 +08:00
汪志鹏 9d87229a30 [MagiHuman] Fix audio sample rate and fps propagation for online serving (#2554) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-04-09 06:52:12 +00:00
pjh4993 ed7a448cd3 [Bugfix] Guard app.state access during server shutdown (#2587) 
Signed-off-by: pjh4993 <pjh4993@naver.com>
 2026-04-09 14:41:23 +08:00
Nick CaoandClaude 3bd8a5239e [Bugfix] Enforce --max-generated-image-size on /v1/images/generations (#2599) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-04-09 03:54:12 +00:00
Zhengyuan Su (苏政渊)andClaude Opus 4.6 c3f1042061 [Feature] End-to-end LoRA support for BAGEL (#2494) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-09 01:33:55 +00:00
Nick CaoandClaude 149b9f179a [Perf][Qwen3-TTS][Voxtral-TTS] Share CUDA graph memory pool across decoder capture sizes (#2386) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-04-08 20:40:17 -04:00
vveerrggandvveerrgg 2c6c07c4f6 [TTS] Add missing _generate_pcm_chunks for OmniOpenAIServingSpeech streaming (#2569) 
Signed-off-by: Yueqian Lin <pandaleefree@gmail.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: vveerrgg <vveerrgg@users.noreply.github.com>
 2026-04-08 22:20:33 +00:00
Dnoob 7e7efdd1ab [Bugfix] Fix benchmark Total input tokens for multimodal requests (#2540) (#2549) 
Signed-off-by: Dnoob <dxpouo@gmail.com>
 2026-04-08 11:00:53 +00:00
R0CKSTAR fb3c6bd9b1 [Feat] Add MUSA flash attention support via mate package (#2451) 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
 2026-04-08 16:01:30 +08:00
Jinhengahengljhnatureofnature
 		c3c736d488 [Feature] Port Bagel RDMA flow to latest main (#2000) 
Signed-off-by: Jinheng Li <ahengljh@gmail.com>
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: ahengljh <ahengljh@users.noreply.github.com>
Co-authored-by: natureofnature <wzliu@connect.hku.hk>
 2026-04-08 14:55:35 +08:00
Lancer 8609bc8ed9 [Feat] image2image for Z-Image (#1580) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
 2026-04-08 14:41:24 +08:00
Yangshen DengandClaude Opus 4.6 1cd5210440 [Diffusion] Refactor LTX2 to use unified CFG parallel framework (#2160) 
Signed-off-by: Yangshen Deng <yangshen.d@outlook.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-08 11:44:04 +08:00
Y. FisherandCanlin Guo ec082add35 [Perf] Wan2.2 I2V optimization: convert datatype from FP32 to BF16 in vae (#2391) 
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
Signed-off-by: Canlin Guo <961750412@qq.com>
Co-authored-by: Canlin Guo <961750412@qq.com>
 2026-04-08 03:26:39 +00:00
Zhengyuan Su (苏政渊)ClaudeSamit
 		cb6a8739c1 [Feature] Add trajectory recording to BAGEL denoising loop (#2483) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Signed-off-by: Zhengyuan Su (苏政渊) <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Samit <285365963@qq.com>
 2026-04-08 10:43:01 +08:00
Yuanheng Zhao 8a55d3d01f [Feat] Enable Layerwise CPU offloading for SD3.5, Ovis-Image, Nextstep_1, LongCat-Image (#2339) 
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
 2026-04-08 09:55:09 +08:00
pikaxingeandAlicia c9dbc0955b [Bugfix] Prevent Silent Stage Dropouts: fix coordinator reconnect bug, close/update race, and heartbeat stall (#1899) 
Signed-off-by: pikaxinge <2392811793@qq.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-04-08 00:48:26 +08:00
Markus / Markandmarksverdhai feefdaee9f [Bugfix] Accept 'speaker' as alias for 'voice' in TTS speech API (#2424) 
Signed-off-by: marksverdhei <marksverdhei@hotmail.com>
Signed-off-by: marksverdhai <249650165+marksverdhai@users.noreply.github.com>
Co-authored-by: marksverdhai <249650165+marksverdhai@users.noreply.github.com>
 2026-04-07 15:07:01 +00:00
汪志鹏 408365fa0d [Bagel]Fused gate_proj and up_proj (#2546) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-04-07 10:02:51 +00:00
汪志鹏 340cba7b04 [daVinci-MagiHuman][Doc][BugFix] Update model support for daVici-MagiHuman and fix media utils bug (#2542) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-04-07 17:16:12 +08:00
skf 9584dd6e69 [HunyuanImage3] Align system_prompt support with official implementation (#2270) 
Signed-off-by: skf1999 <13234016272@163.com>
 2026-04-07 15:37:17 +08:00
Bvicii badbe8eb0f [RFC] Offload blocking TTS/speech ops to thread pool to unblock event loop (#2511) 
Signed-off-by: Bvicii <yizhanhuang2002@gmail.com>
 2026-04-07 00:17:04 -04:00
erfgss 5d4c9ec4fa [bugfix]bugfix dreamid (#2125) 
Signed-off-by: Chen Yang <2082464740@qq.com>
Signed-off-by: erfgss <97771661+erfgss@users.noreply.github.com>
 2026-04-07 12:06:58 +08:00
Alex Brooks 08e2e1fc8e [Bugfix] Fix DataType Handling in Default Diffusion Config (#2530) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
 2026-04-07 11:24:19 +08:00
R0CKSTAR 7a72f34ce4 Add supports_float64() to OmniPlatform and clean up MPS (#2488) 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
 2026-04-07 11:15:02 +08:00
汪志鹏 8dd66ceb00 [BugFix] Continue decode if don't need transfer kv cache between two … (#2502) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-04-07 13:30:01 +12:00
汪志鹏 5b2c4f909d [BugFix] Add bagel text2text/img2text think mode support (#2503) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-04-07 13:29:26 +12:00
Zhengyuan Su (苏政渊) 54e964dc0a [Bugfix] Fix load_weights fallback for non-fused stacked_params_mapping entries (#2523) 2026-04-07 07:28:13 +08:00
Canlin GuoandHongsheng Liu e771842781 [Feature] Support vae tiling parallel encode (#2368) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-06 14:47:45 +00:00
Zhengyuan Su (苏政渊)andClaude 486d77d797 [Feature] Enable LoRA adapter injection for BAGEL (#2490) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Signed-off-by: Claude <noreply@anthropic.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-04-06 19:30:52 +08:00
LancerandDidan Deng 328de586aa [Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-04-06 11:49:35 +08:00
Will.houwillamhouClaudeHappy
 		e23b2634d1 fix(qwen3_tts): align code predictor buffer dtype with model parameters (#2470) 
Signed-off-by: willamhou <willamhou@ceresman.com>
Co-authored-by: willamhou <willamhou@ceresman.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
 2026-04-05 20:54:15 +00:00
Sy03 8b57c6205e [Perf][Fish Speech] Free unused DAC codec components to save VRAM (#2430) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-04-05 20:49:18 +00:00
Sy03andYueqian Lin f6cfacdd16 [Perf][Qwen3-TTS] Free unused decoder in Talker SpeechTokenizer to VRAM (#2429) 
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-04-05 19:04:37 +00:00
Sy03 025408f693 [Fix] [Qwen3-TTS] Qwen3-TTS streaming chunk-boundary artifacts (#2480) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-04-05 14:40:38 -04:00
Yuanheng Zhao 88f7ed9fb6 [Bugfix] Assign original prompt back to RequestOutput (#2498) 
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
 2026-04-05 10:46:11 +00:00
Lancer 832952b2be [Feat] add diffusion pipeline profiler and progress bar support to FluxKontextPipeline et.al (#2489) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-04-05 15:16:11 +08:00
Yuanheng Zhao 094907eeee [Chore] Fix Bagel model import compatibility (#2491) 
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
 2026-04-05 06:47:08 +00:00
indevnandlinyueqian 6fc38e0467 [Model][Core] Enable async_chunk streaming pipeline for CosyVoice3 (#1703) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: indevn <indevn@outlook.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
 2026-04-05 06:11:33 +00:00
Yueqian Lin d92439c155 [CosyVoice3] Fix vLLM 0.19.0 compatibility issues (#2486) 2026-04-05 08:45:49 +08:00
汪志鹏andDidan Deng 0059ec878c [Model Support]: Magihuman support (#2301) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-04-04 09:29:09 +00:00