Commit Graph
17284 Commits
Author SHA1 Message Date
b8a6adadfe [Bug][Spec] fix startup crash and reduce CUDA graph memory usage for speculative adaptive (#35275)
Co-authored-by: alphabetc1 <2508695655@qq.com>
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-27 00:46:13 -07:00
inkcherry 1a91c232ea [AMD][CI] Add targeted Mori test labels (#36636)
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2026-08-27 00:24:02 -07:00
jacky.cheng c967cd19b5 [AMD] Optimize Qwen3.5 MTP unified attention on gfx950 (#36330) 2026-08-27 00:13:49 -07:00
72bf8c4d53 [ci] xpu: trigger pr-test-xpu on multimodal_gen changes (#36100)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
2026-08-27 14:50:26 +08:00
Xun Sun adcf73d7f7 [Weight Cache] Enhance test and support EPLB (#36198) 2026-08-26 23:11:53 -07:00
b294bd4bc7 [CPU][CI]: fix a few issues that cause XEON CI failures (#36413)
Co-authored-by: Zhang, Mingxu <mingxu.zhang@intel.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: MingxuZh <109504044+MingxuZh@users.noreply.github.com>
2026-08-27 13:59:08 +08:00
weireweireandweireweire ea48cb04cc Pin scheduler metadata before asynchronous H2D copies (#35944)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
2026-08-26 22:21:47 -07:00
andyluo7 0f7b5b8b2a [AMD] Add GLM-5.3-Flash recipes for MI300X, MI325X, and MI355X (#36608) 2026-08-27 05:19:57 +00:00
jacky.cheng f775db03aa [AMD] Fix int32 seqused_k overflow in aiter draft-extend attention (#36541) 2026-08-26 22:06:39 -07:00
weireweireandweireweire 4d5d506486 Publish gated DSV4 DFLASH-family target-prefill read completion (#35947)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
2026-08-26 21:33:08 -07:00
Xun Sun 7324021e6c [CI] Grant no-cooldown for UNIDY2002 (#36609) 2026-08-27 12:13:59 +08:00
sglang-botandsglang-bot e6c1a3cd4c docs: sync LMSYS SGLang blog cards (#35416)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
2026-08-27 03:56:54 +00:00
Alison Shao 02dfd37826 [CI] Remove GLM-4.1V-9B-Thinking from nightly VLM MMMU eval (#36602) 2026-08-26 20:29:38 -07:00
Jialin Ouyang a2b589fdf8 [Radix Cache] Add test-only TreeCore inspector for shared backend tests (#35791) 2026-08-27 11:17:51 +08:00
a3ae667d67 [Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend (#35634)
Co-authored-by: menyu <menyu@nvidia.com>
Co-authored-by: Jinyan Chen <93358689+liz-badada@users.noreply.github.com>
Co-authored-by: Han Yu <helloyu0903@gmail.com>
Co-authored-by: Cheng Wan <cheng.wan@radixark.ai>
2026-08-26 19:54:33 -07:00
AMD-yanfeiwang cbfe54fba8 [AMD] Use fast exponentials in C4 and C128 ROCm kernels (#34296) 2026-08-26 19:49:01 -07:00
Michael 1c8f2b38cb [AMD][CI] Add DeepSeek-V4-Flash FP8 accuracy coverage on MI30x (#36396) 2026-08-26 19:30:07 -07:00
MickandClaude Opus 5 07570202f0 [VLM] route every multimodal processor through the worker pool's call site (#35342)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 10:27:45 +08:00
Zaili Wang 5adc2880f9 [CPU] Enable ERNIE models on CPU (#35222) 2026-08-27 10:13:10 +08:00
Promisewjx 9d07b9e227 [Performance] Reduce idle DP work in breakable prefill CUDA graphs (#33871) 2026-08-27 10:09:54 +08:00
Bingxu Chen 4f59a8dcfa [AMD][Bugfix] Skip invalid fused MoE reduction for direct top-1 output (#36309) 2026-08-26 18:52:15 -07:00
Haotong Zou b658d64d5b [CPU] Fix rotary_embedding_cpu fake for in-place layouts (#36443) 2026-08-27 09:48:07 +08:00
Bingxu Chen d2b3e9051d [AMD][CI] Stabilize PyTorch sampling backend test on ROCm (#36307) 2026-08-26 18:44:10 -07:00
Haotong Zou 058f99c561 [CPU] Fix truncated KV prefix in intel_amx spec verify (#36430) 2026-08-27 09:42:36 +08:00
Alison Shao 15688fea7d Fix BailingMoeV3 reading enable_dp_lm_head off live topology instead of config (#36584) 2026-08-26 18:41:39 -07:00
ashwini rathi a8b72c4c34 [Intel XPU] Fix cross-encoder rerank hang on B580 runners (#36360) 2026-08-27 09:33:20 +08:00
Bingxu Chen 862f9ed3d8 [AMD] Fall back to CPU tensor for decode retraction on ROCm (#36343) 2026-08-26 18:32:51 -07:00
20621aa14b [Model] Support Ling-3.0-flash (BailingMoeV3) (#33561)
Signed-off-by: JustinTong <justintong0323@gmail.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: 得泽 <zhangkaihong.zkh@antgroup.com>
Co-authored-by: 翎悦 <vito.yy@antgroup.com>
Co-authored-by: 羽癫 <yudian.zy@antgroup.com>
Co-authored-by: tiwei.btw <tiwei.btw@antgroup.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: 文赋 <zibin.zb@antgroup.com>
Co-authored-by: JustinTong <justintong0323@gmail.com>
2026-08-26 17:27:23 -07:00
paulzhang-tm 8739d56a31 [Spec] Generalize hybrid SWA MTP draft pool routing (#35379) 2026-08-26 17:02:36 -07:00
ec4bdbfa4a [Feature] Beam search support (#31626)
Co-authored-by: cswuyg <cswuyg@gmail.com>
Co-authored-by: cswuyg <496090217@qq.com>
Co-authored-by: Vedant Jhaveri <vedantjh2@gmail.com>
Co-authored-by: Vedant Jhaveri <vjhaveri@linkedin.com>
2026-08-26 16:56:15 -07:00
Cheng Wan e5a1c5a423 Fix _is_compiling dynamo tracing: import torch instead of sys.modules lookup (#36573) 2026-08-26 16:17:02 -07:00
kuma_Gu2006 7f27bf4708 [Kernel] Declare the PyTorch ABI dependency in sglang-kernel wheels (#36465) 2026-08-26 15:24:26 -07:00
Trevor Morris 1eb629ab4f [NVIDIA] Tune custom all reduce v2 for sm_107 (#36397) 2026-08-26 15:19:31 -07:00
Trevor Morris 3ce243da3f [NVIDIA] Add CUDA 13.4 container for initial Rubin support (#36233) 2026-08-26 15:02:16 -07:00
paulzhang-tm 06694071c6 [Spec] Avoid tensor scalar reads in spec decode allocation (#35377) 2026-08-26 14:51:31 -07:00
Liangsheng Yin 45c85c198b [CI] Lower the AWQ Marlin MMLU threshold to 0.80 (#36570) 2026-08-26 14:43:20 -07:00
Xinyuan Tong a8d716ce8d dsa: widen the fp8 k-cache quant kernel's token_id to int64 (#30859) 2026-08-26 14:22:24 -07:00
Mohammad Miadh AngkadandMohammad Angkad 2935bb8e79 Fix OOB read in mxfp4 MoE weight scales on Hopper (#36456)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-08-26 13:36:49 -07:00
siyu e7e7894016 [Weight Cache] Make daemon socket/ready paths configurable via env (#36299) 2026-08-26 12:38:50 -07:00
weireweireandweireweire 5263568bcb [HiCache] Keep auxiliary load-back out of Full KV pending ownership (#36317)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
2026-08-27 01:30:38 +08:00
Xinyuan Tong e27a7fac77 GLM-5.3-Flash cookbook: default Blackwell recipes to FP8 KV + TRT-LLM DSA (#36519) 2026-08-27 00:51:05 +08:00
Xinyuan Tong f8cc1f9525 GLM-5.3-Flash cookbook: FP8 KV + TRT-LLM DSA benchmark card (#36513) 2026-08-26 07:39:27 -07:00
Shangming Cai c8b56b1f44 chore: bump mooncake version to 0.3.13 (#36493) 2026-08-26 22:21:15 +08:00
XuFuandMick 924aeee59c [diffusion] feat: support batching for cosmos3 action generation (#36301)
Signed-off-by: FxxxxU <fu18801374388@163.com>
Signed-off-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-08-26 22:15:03 +08:00
Xinyuan Tong dfc40e0efe Add GLM-5.3-Flash cookbook (#36440) 2026-08-26 07:00:16 -07:00
Yuhao Yang 8eaffdf382 docs: point the Qwen3.8-Flash-Next cookbook at model support PR #36497 (#36499) 2026-08-26 12:53:55 +00:00
c7b5e76fa9 Add Qwen3.8-Flash-Next cookbook (#36496)
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-26 20:36:59 +08:00
Cheng Wan 413df1f8db config: ServerArgs holds the raw input (#36255) 2026-08-26 05:14:05 -07:00
27c36368b6 fix(moe): guard FP8 delegate activation params (#36275)
Signed-off-by: jikuixie <jikuixie@gmail.com>
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Co-authored-by: shyeh25 <206795756+shyeh25@users.noreply.github.com>
2026-08-26 12:12:21 +00:00
Cheng Wan 937af8538b config: the runtime readers take the published bags (#36254) 2026-08-26 05:08:25 -07:00