Commit Graph
2650 Commits
Author SHA1 Message Date
R0CKSTAR ab0da662c0 [Hardware] Enable CosyVoice3 on Moore Threads MUSA (#5164)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2026-07-29 02:46:27 +00:00
Zhang Jian fa41fdf252 [recipe][NPU] add cosmos3-super recipe on 8xA3 (#5097)
Signed-off-by: Zhang Jian <jianmusings@gmail.com>
2026-07-29 08:29:33 +08:00
Joshna-MedisettyandChendi.Xue 7fa40681ff Xpu/vllm 0.26 fixes (#5476)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
2026-07-29 08:15:36 +08:00
iancarrasco-b10 23bb4395bb [Feature] Flush the speech WebSocket on input.done without closing it (#5517)
Signed-off-by: iancarrasco-b10 <ian.carrasco@baseten.co>
2026-07-28 23:46:19 +00:00
Sy03andHongsheng Liu 0feb92bdfa [Bugfix][Minicpm] Support full-duplex three-stage serving (#5380)
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-29 01:58:34 +08:00
张芷瑜(Zhang Zhiyu)andZhiyu0603 f6e59c329b [Bugfix] Return diffusion metrics from /v1/images/generations (#5278)
Signed-off-by: Zhiyu0603 <Zhiyu0603@users.noreply.github.com>
Co-authored-by: Zhiyu0603 <Zhiyu0603@users.noreply.github.com>
2026-07-28 16:38:37 +00:00
Inesh Reddy Chappidi c96fe54bd8 [Test] Add regression test for MiniCPM-o 4.5 audio-stream output kinds (#5356)
Signed-off-by: Inesh Reddy <ineshreddy249@gmail.com>
2026-07-28 16:27:51 +00:00
c2b55de5b9 [Test] Give the logprobs scheduler doubles the vLLM 0.26 contracts (#5483)
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: tzhouam <tzhouam@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
2026-07-28 15:25:57 +00:00
Canlin Guo 61324e65d7 [Refactor] Make MOSS-TTS-Local stream session dynamic batch (#5235)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
2026-07-28 21:38:24 +08:00
Hongsheng Liu f775e80732 Revert "[BugFix] Fix 'GPUARWorker' attribute error" (#5507) 2026-07-28 21:00:49 +08:00
herotai214 c96f0bc773 [Perf][GLM-Image] Skip redundant hidden state D2H (#5346)
Signed-off-by: herotai214 <herotai214@gmail.com>
2026-07-28 20:34:35 +08:00
Ting FU f4640d9a2e [BugFix] Fix 'GPUARWorker' attribute error (#5478)
Signed-off-by: Semmer <semmer@live.cn>
2026-07-28 20:13:33 +08:00
Mu GuanLin 12d75cf63a [Feature] Add official LTX multimodal guidance and precision guard (#5148)
Signed-off-by: mglyn <1203789601@qq.com>
2026-07-28 10:44:25 +00:00
Zhou TaichangandClaude Opus 5 66a9b0c84f [Bugfix] Select the AR-Diffusion engine in the DreamZero CFG-parallel deploy config (#5439)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-28 17:14:26 +08:00
wangyu cee2e40c33 [CI] Skip known-failing tests and filter NPU ready TTS by npu mark (#5489) 2026-07-28 15:26:36 +08:00
5014fea4a0 [New Model] support nemotron Audex (#4976)
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-07-28 03:58:22 +00:00
Weiming Liaoandwangyu f2c5152df0 [CI][NPU]: Add nightly performance test for NPU - qwen3-omni/wan2.2/qwen-image-edit-2511 (#5339)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
2026-07-28 11:44:30 +08:00
WeiandSamit d3e0171cd7 [bugfix] validate AR sampled-token logprob alignment (#5273)
Signed-off-by: hbhflw2000 <417911774@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
2026-07-28 10:34:19 +08:00
Joshna-Medisetty 807db6efd7 [Refactor] Migrate Voxtral TTS XPU stage config to --deploy-config (#5467)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
v0.26.0rc1
2026-07-28 07:35:35 +08:00
Yueqian LinandSy03 d4a5eaac90 [Bugfix][Realtime] Stop disconnected sessions from cycling through stages (#5388)
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Sy03 <1370724210@qq.com>
2026-07-27 17:04:17 +00:00
Yueqian Lin 8f115164c2 [Bugfix][Connectors] Flush processor tail on terminal async-chunk sends (#5414)
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-07-27 16:04:08 +00:00
cbab1d4d8f [Rebase] Rebase to vllm 0.26.0 (#5443)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: tzhouam <tzhouam@gmail.com>
2026-07-27 23:35:49 +08:00
LHXuuuandYuanheng Zhao fb89ab43ea [Refactor][Ming-TTS] Move speaker extraction and caching to Stage-0 (#5351)
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
2026-07-27 07:55:47 -07:00
SYLARandlishunyang12 7762d664d8 [Attention] Add trtllm diffusion attention backend with Skip-Softmax (#5283)
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
2026-07-27 22:48:11 +08:00
Wang fuyinandHongsheng Liu 4dd1b47f47 [Config] Read stage metadata from VllmOmniConfig (#5343)
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-27 22:44:06 +08:00
e108cbb510 [NPU][HunyuanImage3] Adapt diffusion FusedMoE for vLLM >= 0.24.0 (#5167)
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-27 22:41:34 +08:00
ruirui(rein) yangandamy-why-3459 82172b112d [BugFix][MiniCPM-o] Restore audio output without async chunk (#5455)
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-07-27 22:19:46 +08:00
汪志鹏 e9bc7fc06a [Refactor]: Mammothmoda2-dev use x_to_text.py in examples (#5454)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-27 14:11:49 +00:00
zzh 8001bb155d Fix missing sequence_parallel_size in deploy config output (#5449)
Signed-off-by: zzh <943967662@qq.com>
2026-07-27 02:15:08 -07:00
汪志鹏 88b7ca2ffa [Model] Support MammothModa2-Dev (#5411)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-27 17:01:54 +08:00
rein yang 5b230541c9 [Deploy] Reduce MiniCPM-o single-GPU startup memory (#5447)
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
2026-07-27 16:37:25 +08:00
Zhou TaichangandClaude Opus 4.8 776424f0de [Refactor][WIP] Add missing test for modelrunner (G1/N) (#5333)
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-27 16:24:47 +08:00
xsmcccandxsmccc d688aa82fc [Model] Optimize MiniCPM-o multimodal encoder memory (#5188)
Signed-off-by: xsmccc <247721718+xsmccc@users.noreply.github.com>
Co-authored-by: xsmccc <247721718+xsmccc@users.noreply.github.com>
2026-07-27 15:24:51 +08:00
WeiQing Chen 9b4ea13c80 docs: update WeChat QR code (#5430)
Signed-off-by: David Chen <530634352@qq.com>
2026-07-27 14:30:15 +08:00
Zeyu Huang | 黃澤宇 eaf90d8eff [Frontend] Add midway prompt update for streaming video generation (#4652)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
2026-07-27 14:07:43 +08:00
wjsuijlenh 1f01d05603 [Core] Session state manager for AR-diffusion world models (RFC #4480 Phase 0) (#4487)
Signed-off-by: Wijnand Suijlen <wijnand.suijlen@huawei.com>
2026-07-27 13:17:38 +08:00
Inesh Reddy Chappidi 9f3a73df17 test: make Qwen-Image diffusers-backend latency check fair and stable (#5108) (#5132)
Signed-off-by: Inesh Reddy <ineshreddy249@gmail.com>
2026-07-26 22:14:26 -07:00
Zheng Wengang b9b8282cf5 [BugFix] Couple audio+video mm-cache for use_audio_in_video (#5308)
Signed-off-by: ZhengWG <zwg0606@gmail.com>
2026-07-27 04:29:53 +00:00
Yash Jain 911ea0c586 [Bugfix][Frontend] Parse VLLM_USE_MODELSCOPE via vllm.envs (#5428)
Signed-off-by: Yash Jain <yashjainjain1704@gmail.com>
2026-07-27 04:19:22 +00:00
Wallbreazzz e28e389a76 feat(qwen3-tts): add codec_chunk_ramp for gradual chunk size warmup (#5152)
Signed-off-by: Wallbreazzz <110282866+Wallbreazzz@users.noreply.github.com>
2026-07-27 04:15:43 +00:00
zhumingjue138 138c6988ad [Bugfix] skip test case for #5437 (#5440)
Signed-off-by: zhumingjue <zhumingjue@huawei.com>
2026-07-27 11:47:59 +08:00
汪志鹏 ddc3c87547 [Refactor][Docs]: Remove stale BAGEL offline guide (#5429)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-27 09:46:11 +08:00
SYLARandlishunyang12 2bb618903a [Recipe] Add Cosmos3-Edge (#5313)
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
2026-07-26 09:25:00 +00:00
汪志鹏 ccdb2b51aa [Refactor]: Intrduce x_to_text.py in examples (#5384)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-07-26 16:33:17 +08:00
b6c4578dac [BugFix]Add MiniCPM-o 4.5 end-to-end test suite (offline, online serving) (#5237)
Signed-off-by: y_null <y_null@qq.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-25 17:00:13 -07:00
boatman 76e4a78afc [Bugfix][Higgs-Audio-V3] Propagate Sampling Parameters to Sampler (#5406)
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
2026-07-25 15:25:35 +00:00
af2f84582b perf(qwen3-tts): cache decoder masks and compile pre-transformer (#5107)
Signed-off-by: Ziyang Zhang <hafuhafu@qq.com>
Co-authored-by: Sy03 <1370724210@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-25 08:09:19 +00:00
wangyu 7afd3a0dcb [CI/Bugfix] Pin dev deps and downgrade mooncake for connector CI (#5389) (#5392) 2026-07-25 13:03:19 +08:00
Sy03 e043818abf [Bugfix][Frontend] Remove async-chunk guard from realtime API (#5383)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-07-25 09:20:47 +08:00
akshatvishu d6240742f3 [BugFix][CI] Upgrade ROCm and CUDA docker base images to v0.25.0 (#5115)
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
2026-07-24 18:18:32 +00:00