kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-11 01:36:58 +00:00
Code Issues Packages Projects Releases Wiki Activity
6,591 Commits 157 Branches 0 Tags
3a64844a1cffd96289a756d2c9ea34ce669febbc
Commit Graph

4391 Commits

Author SHA1 Message Date
Nicolas Castet
3a64844a1c Fix hang in deepgemm compilation with symmetric memory enabled (#12715) 2025-11-06 14:06:22 -08:00
Lee Nau
b0d1c21d03 [fix] Only enable flashinfer all reduce fusion by default for single-node servers (#12724) 2025-11-06 11:53:58 -08:00
R0CKSTAR
b07c5e4080 Pin uvloop to 0.21.0 (#12279) 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
 2025-11-07 03:33:31 +08:00
jianan-gu
6e6009fb6b [CPU] Fix TP padding case with weight block size (#8243) 2025-11-07 03:24:48 +08:00
Jimmy
88a2a34041 [Fix]HTTP Stream raise exception (#11904) 2025-11-07 03:23:12 +08:00
Teng Ma
78c58621d2 [mem pool] bugfix: wrong position for self.device in Mamba (#12684) 2025-11-07 03:05:42 +08:00
gaopengff
4e234b4cf9 [Intel XPU]Update pytorch xpu to 2.9 (#12363) 2025-11-06 10:34:23 -08:00
gaopengff
4cc725ac1c [Intel]Add 'intel_xpu' attention backend for llama4 (#11051) 2025-11-06 10:33:41 -08:00
sglang-bot
0c006b8809 chore: bump SGLang version to 0.5.5 (#12739) 2025-11-07 00:46:19 +08:00
Ke Bao
cd135bfe30 Update dsv3 quantization auto setting for sm100 (#12778) 2025-11-06 22:39:13 +08:00
jiapingW
0da30dbc20 fix qwen3-omni audio length < 30s (#12674) 
Co-authored-by: canghua <canghua.wjp@alibaba-inc.com>
 2025-11-06 00:05:28 -08:00
yinghui
58095cb00a Add timing metrics for requests (#12646) 
Co-authored-by: Scott Lee <scottjlee@users.noreply.github.com>
 2025-11-05 23:07:16 -08:00
Yuan Luo
fd3034da75 [VLM] Optimize qwen_vl preprocess_video (#12240) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: 羽癫 <yudian.zy@antgroup.com>
 2025-11-06 14:55:01 +08:00
Binyao Jiang
fbbe16faab [GDN] Fuse b.sigmoid(), fused_gdn_gating and unsqueeze into one kernel: up to 0.85% e2e speedup (#12508) 2025-11-05 22:52:04 -08:00
Yi Zhang
6a1a64fa41 [BUGFIX] fix output_ids in abort (#12737) 2025-11-05 22:51:47 -08:00
Yi Zhang
e2715cf871 fix mamba prefix cache leak caused by abort (#12693) 2025-11-05 22:51:03 -08:00
Mick
73e9a2ef5c fix: tiny fix cli (#12744) 2025-11-06 14:45:50 +08:00
Atream
2104d20eba Temporarily fix missing routed_scaling_factor for CompressedTensorsWNA16MoEMethod (#12738) 2025-11-06 12:01:03 +08:00
YAMY
f235498eca DeepSeek-V3.2: Add Adaptive MHA Attention Pathway for Short-Sequence Prefill (#11892) 2025-11-05 19:33:26 -08:00
gongwei-130
97be66c358 fix sgl-kernel version (#12723) 2025-11-05 19:01:03 -08:00
Lianmin Zheng
c7d57d5bb3 Fix CI and style (#12658) 2025-11-05 15:08:15 -08:00
Kaixi Hou
141278048e [NVIDIA] Fix unit test of MoE and add it to nightly ci (#12709) 2025-11-05 14:33:18 -08:00
Shu Wang
82f39dc11d Add mm_fp4 trtllm backend (#12406) 2025-11-05 14:31:46 -08:00
Atream
627bac649c Support Expert Deferral Mechanism in KTransformers (#12586) 
Co-authored-by: Chen Hongtao <56470055+chenht2022@users.noreply.github.com>
Co-authored-by: chenht2022 <cht22@mails.tsinghua.edu.cn>
 2025-11-05 13:41:52 -08:00
Morpheus Guo
c8547ecddd Enable Aiter Attention for VL model (#12699) 
Co-authored-by: yuechguo <yuechguo@amd.com>
 2025-11-05 13:01:23 -08:00
Mick
7bc1dae095 WIP: initial multimodal-gen support (#12484) 
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: JiLi <leege233@gmail.com>
Co-authored-by: CHEN Xi <78632976+RubiaCx@users.noreply.github.com>
Co-authored-by: laixin <xielx@shanghaitech.edu.cn>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: jzhang38 <a1286225768@gmail.com>
Co-authored-by: BrianChen1129 <yongqichcd@gmail.com>
Co-authored-by: Kevin Lin <42618777+kevin314@users.noreply.github.com>
Co-authored-by: Edenzzzz <wtan45@wisc.edu>
Co-authored-by: rlsu9 <r3su@ucsd.edu>
Co-authored-by: Jinzhe Pan <48981407+eigensystem@users.noreply.github.com>
Co-authored-by: foreverpiano <pianoqwz@qq.com>
Co-authored-by: RandNMR73 <notomatthew31@gmail.com>
Co-authored-by: PorridgeSwim <yz3883@columbia.edu>
Co-authored-by: Jiali Chen <90408393+gary-chenjl@users.noreply.github.com>
 2025-11-05 12:28:52 -08:00
Lianmin Zheng
fb2e816e83 Fix server args for gpt oss so users can override the moe runner backend (#12696) 2025-11-05 11:36:59 -08:00
bigmoyan
508d2f7aa2 add Kimi k2 reasoning parser (#12702) 
Signed-off-by: wangzhengtao <wangzhengtao@msh.team>
 2025-11-06 00:37:54 +08:00
Yuxuan Zhang
a889c85459 [Grammar Fix] GLM-4-MOE self.first_k_dense_replace is undefined. (#12455) 2025-11-06 00:03:45 +08:00
Yuhong Guo
4d84f886e7 Refactor --debug-tensor-dump-layers to list (#12691) 2025-11-05 03:30:01 -08:00
yinghui
dc4f541823 fix trtllm_mla attention backend when disabling cuda graph. (#12687) 2025-11-05 01:35:02 -08:00
zejunchen-zejun
0648eb482d [Profiler] Add SGLANG_PROFILE_RECORD_SHAPES for recording shapes when profiling (#11641) 
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
 2025-11-04 23:41:46 -08:00
yinghui
b88fab3111 fix: add seed bench_serving to cache key, remove redundant function definition. (#12680) 2025-11-04 23:39:11 -08:00
Glen Liu
cbf23dbbfa [Feature] add --lora-request-distribution arg to bench_serving.py and support skewed and distinct workloads (#12175) 2025-11-04 21:41:40 -08:00
ai-easy-cpu
48641435d6 fix typo of args description in sglang.profiler (#12486) 
Co-authored-by: AI-bot-easy <litchys0123@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-04 20:15:13 -08:00
Liangsheng Yin
44b1b394a4 [PD-Disagg] Check finish after pop tranferred (#12638) 2025-11-05 11:18:09 +08:00
Kaixi Hou
0711d1509b [NVIDIA] Fix cutedsl backend of MoE (#12353) 2025-11-04 18:54:55 -08:00
sglang-bot
09938e1f82 chore: bump SGLang version to 0.5.4.post3 (#12639) 2025-11-04 18:32:11 -08:00
Nicolas Castet
2340798353 Register allgather/reducescatter buffers with symm memory (#12572) 2025-11-04 17:11:36 -08:00
soaringk
44da737770 [fix] Handle escaped characters in GLM tool call parser to prevent double serialization (#12456) 2025-11-04 16:48:14 -08:00
Baizhou Zhang
d22d044734 Revert "Enable memory saver for hybrid model" (#12648) 2025-11-04 16:22:06 -08:00
Kaixi Hou
34f7564df0 [NVIDIA] Fix wrong symmetric sizes for fp4 cases (#12640) 2025-11-04 14:19:37 -08:00
Johnsonms
1cfbbc42d8 [Bug] Fix NSA Backend KV-Buffer Shape Mismatch in DeepSeek-V3.2 (#12645) 2025-11-04 13:57:32 -08:00
Lianmin Zheng
55dfb539cf [Auto Sync] Update scheduler_metrics_mixin.py, collector.py (20251104) (#12647) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
 2025-11-04 13:56:14 -08:00
Baizhou Zhang
42889acbd0 [hotfix] Fix deepep w4a8 bug (#12642) 2025-11-04 13:55:59 -08:00
Trevor Morris
211f4070e5 fix: Lazy import mooncake-ep to fix extra gpu contexts being created (#12641) 2025-11-04 12:28:36 -08:00
Liangsheng Yin
befa41a152 Fix output_ids inconsistency (#12628) 2025-11-05 01:43:08 +08:00
Liangsheng Yin
30b26ee9d0 Add io struct naming check back (#12634) 2025-11-05 01:15:01 +08:00
Liangsheng Yin
aa797d013d [Test] Merge all constrained decoding tests. (#12633) 2025-11-05 00:43:06 +08:00
Ke Bao
7cee07a067 Fix skip layer in get_quant_method (#12632) 2025-11-04 23:27:46 +08:00