chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity
7,449 Commits 1 Branch 0 Tags
d6c490192d12a5191b83c2dbc1255a91d8717a6c
Commit Graph
4911 Commits
Author SHA1 Message Date
Chunyuan WU 8fcc69e7c4 Turn on shm_allreduce and shm_allgather for fp16 (#10725) 2025-10-17 12:35:20 -07:00
ykcombat f440baa136 [Feature] Reuse flashinfer workspace for PD-Multiplexing. (#11540) 2025-10-18 02:35:06 +08:00
Yineng Zhang da681f35d3 Revert "Set csgmv as default lora backend. (#11488)" (#11735) 2025-10-17 12:01:36 -05:00
pdasgupandXinyuan Tong 9b0f725b1d add tuned fuse moe kernel for qwen3 235b fp8 on h200 (#11730) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-10-17 09:55:09 -07:00
Liangsheng Yin cde5a6e30f Abstraction for spec worker and code cleanup (#11643) 2025-10-17 23:31:36 +08:00
Mick 3e4c7da2f5 ci: reduce and refactor vlm ut and combine test files (#11062) 2025-10-17 15:24:50 +00:00
Liangsheng Yin d88ac9bc9a [overlap-spec] Make plan stream an option (#11724) 2025-10-17 15:48:57 +08:00
Liangsheng Yin ce11dd82dc [CI] Try fix broken event loop init (#11746) 2025-10-17 13:30:17 +08:00
StonyPortandqiuxuan.lzw fd389df96e Reduce the image processing latency in VLM (#11541) 
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
 2025-10-16 15:00:03 -07:00
Baizhou Zhang b0d1d717e1 Revert "make radix cache deterministic" (#11728) 2025-10-16 14:36:15 -07:00
Simo Lin 4f24ab1718 [router][grpc] add dissag info to warm up in grpc server (#11727) 2025-10-16 14:19:55 -07:00
MickandXinyuan Tong 86b04d25b3 model: qwen3-omni (thinker-only) (#10911) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-10-16 13:20:38 -07:00
sglang-botandsglang-bot 85ebeecf06 chore: bump SGLang version to 0.5.3.post3 (#11693) 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
 2025-10-16 13:14:55 -07:00
Hank Han 0dd6cf16ba [ci]use H20 to run disaggregation test (#11543) 2025-10-16 11:42:42 -07:00
Even Zhou 3cceaa381a [Bugfix] Fix Qwen3/DSV3/DSV3.2 model support (#11510) 2025-10-16 15:14:09 +08:00
Lifu Huang b0d20cdec7 Set csgmv as default lora backend. (#11488) 2025-10-15 23:53:24 -05:00
YanbingJiangandMa Mingfei cbac499750 Split test_intel_amx_attention_backend.py to pass CI of timeout (#11370) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2025-10-15 19:22:32 -07:00
Shangming Cai 476c67d7fc Fix missing a2a backend init of GLM4.5 MoE Block (#11692) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2025-10-15 19:13:08 -07:00
Shangming Caihzh0425ZeldaHuang
 		868403f642 [PD] Add PD support for hybrid model (Qwen3-Next, DeepSeek V3.2 Exp) (#10912) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: ZeldaHuang <hzm414167@alibaba-inc.com>
 2025-10-15 18:59:14 -07:00
Hanming Lu 97d857c096 [Mamba] Increase default mamba_full_memory_ratio to 0.9 (#11679) 2025-10-16 09:56:43 +08:00
Lianmin Zheng cd7e1bd591 Sync code and test CI; rename some env vars (#11686) 2025-10-15 18:37:03 -07:00
Huaiyu, Zheng 729b7edf72 enable rmsnorm on XPU (#10248) 2025-10-15 17:54:18 -07:00
DiweiSunhuaiyuzhMa Mingfeicoderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 		4c03dbaaef [CI][XPU]enable sglang CI on Intel XPU (#9493) 
Co-authored-by: huaiyuzh <huaiyu.zheng@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-10-15 17:13:19 -07:00
sglang-botandsglang-bot baf277a9bf chore: bump SGLang version to 0.5.3.post2 (#11680) 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
 2025-10-15 16:49:14 -07:00
Chang Su f226d3da2a Fix missing json imports in serving_responses.py (#11681) 2025-10-15 13:01:55 -07:00
Chang SuandXinyuan Tong 30ea4c462b [tool call] Fix prev_tool_call_arr management in base_format_detector.py (#11367) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-10-15 09:51:51 -07:00
Shangming CaiandLiangsheng Yin 6d0364681c Fix 1-step draft model forward (#11653) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2025-10-15 19:11:33 +08:00
Liangsheng Yin 8221f9ae8b Tiny cleanup some eagle unused codes (#11660) 2025-10-15 17:24:08 +08:00
Stefan He 6b143d62a2 Clean up some Qwen3-Next and deterministic code (#11585) 2025-10-15 15:19:37 +08:00
Zheng Wengang b2c8566920 [BugFix][Qwen3-VL]: fix cu_seqlens in qwen3-vl (#11458) 2025-10-14 22:16:49 -07:00
Yineng Zhang 91fc5bb5a9 feat: add add_chunked_prefix_cache_attention_backend (#11636) 2025-10-14 21:48:13 -07:00
Lifu Huang 780fbf2f38 [Fix] Fix accuracy bug in CSGMV kernel caching key. (#11579) 2025-10-14 20:25:56 -07:00
JinwuandHank Han 825432fce6 [1/N]Support DeepSeek-R1 w4a8 normal deepep (#8247) 
Co-authored-by: Hank Han <hanhan7630@outlook.com>
 2025-10-14 20:10:53 -07:00
Xun SunHank HanShangming Cai
 		a40229f6f8 [1/N] Introduce Mooncake Backend and Mooncake EP to Support Elastic EP (#10423) 
Co-authored-by: Hank Han <hanhan7630@outlook.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2025-10-14 19:40:54 -07:00
Sahithi Chigurupatiandzhyncs e9e120ac7a fix: upgrade transformers to 4.57.1 (#11628) 
Signed-off-by: Sahithi Chigurupati <chigurupati.sahithi@gmail.com>
Co-authored-by: zhyncs <me@zhyncs.com>
 2025-10-14 18:35:05 -07:00
cctry 1d7f783501 Refactor kv cache free (#11351) 2025-10-14 17:45:19 -07:00
Simo LinandChang Su 325951460f [router][grpc] add warm up to grpc server (#11627) 
Co-authored-by: Chang Su <chang.s.su@oracle.com>
 2025-10-14 16:11:16 -07:00
DarkSharpness e28c9e526f [Minor] Update xgrammar dependency (#11622) 2025-10-14 13:46:50 -07:00
Lianmin Zhenggithub-actions[bot] <github-actions[bot]@users.noreply.github.com>Byron Hsu
 		b98cf39866 [Auto Sync] Update collector.py (20251014) (#11625) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
 2025-10-14 13:34:33 -07:00
Lianmin Zhenggithub-actions[bot] <github-actions[bot]@users.noreply.github.com>Stefan He
 		27d710457c [Auto Sync] Update scheduler.py, server_args.py (20251014) (#11623) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
 2025-10-14 13:20:03 -07:00
Baizhou Zhang c224a4c6cc Fix log for chunked prefix cache (#11624) 2025-10-14 11:49:33 -07:00
strgrb 94d26d850d use non_blocking h2d in ForwardBatch.prepare_mlp_sync_batch. (#11605) 2025-10-14 11:30:59 -07:00
Liangsheng Yin 5ea96ac7cc Reduce one step decode for draft model. (#11561) 2025-10-14 23:52:04 +08:00
yinghuiandLianmin Zheng 56222658ec move eagle draft post process to cuda graph (#11434) 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
 2025-10-14 22:50:53 +08:00
Alex Chi Z dc965db0e0 make radix cache deterministic (#10721) 
Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
 2025-10-14 21:01:52 +08:00
Scott Lee 817e46f412 Refactor spec decoding metrics calculation into separate TokenizerManager utility function (#11586) 2025-10-14 20:45:49 +08:00
Liangsheng Yin 5a33c3aae7 Optimize Triton Draft Backend (#11556) 2025-10-14 20:08:32 +08:00
Qiaolin Yu e4358a4585 Add fused_moe_triton config: triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200.json (#11587) 2025-10-14 13:24:43 +08:00
Lianmin Zhenggithub-actions[bot] <github-actions[bot]@users.noreply.github.com>Hanming Lu
 		ba2ce28fe9 [Auto Sync] Update model_config.py (20251014) (#11580) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
 2025-10-13 22:16:34 -07:00
Chenxi Li 28f80b1244 Implement LRU eviction policy for LoRA adapters (#11041) 2025-10-13 20:18:25 -07:00