minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
15,413 Commits 2 Branches 0 Tags
48ae829f6e47f9348d8bd936b102d4d7a76f2743
Commit Graph
10494 Commits
Author SHA1 Message Date
Ke Bao 48ae829f6e Reset only the used mamba state on unified radix cache (#31648) 2026-07-18 21:43:13 +08:00
chx96642264 d7b9425529 [NPU] fix: skip Triton embedding kernel on NPU to avoid kernel launch failure (#31636) 2026-07-18 19:32:03 +08:00
Xiaoyu ZhangandClaude Opus 4.8 216b750c8f [Kernel] Sweep decoupled scattered kernels into sglang.kernels.ops (RFC #29630) (#31582) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-18 19:07:07 +08:00
Yaochen Hanyhyang201Mick
 		9306278fbc vlm: batch cross-request vit encoding and reuse attention metadata (#24013) 
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-07-18 18:50:33 +08:00
Gabriel Wu faf6894093 Implement SM120 DeepSeek V4 flashinfer_mxfp4 moe runner backend + TP2 (#30272) 2026-07-18 03:01:06 -07:00
Mick 6c6175fabd perf: avoid excessive prefill CUDA graph padding (#31487) 2026-07-18 16:25:30 +08:00
twb1235andZhiqiang Xie 071e649288 fix(rpc) Synchronize RPC requests only within the TP group. (#25213) 
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
 2026-07-18 07:44:51 +00:00
ThanhhaoandHao Phan 72c4ed1a3f [Spec] DFlash: remove per-step host syncs so the CPU runs a full step ahead (spec-v2 overlap) (#31468) 
Co-authored-by: Hao Phan <htphan@nvidia.com>
 2026-07-17 23:22:07 -07:00
Khoa PhamandClaude Opus 4.8 7a896215e7 [CP] Migrate MLA prefill CP (DeepSeek V3) to CP-v2 zigzag strategy (#31619) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-17 22:37:53 -07:00
Liangsheng Yin 639261f7b2 [Refactor] Move output logprob processing into the logprob_processor layer (#31624) 2026-07-17 22:33:52 -07:00
Liangsheng Yin 19c53c44a0 [Fix] Account zero-logprob sequences correctly in chunked logprob stitching (#31639) 2026-07-17 22:33:27 -07:00
DevashishLal-CBandDevashish Lal ab3d421c30 [plugin] oot torch profiler activity support (#31580) 
Signed-off-by: Devashish Lal <devcode@fb.com>
Co-authored-by: Devashish Lal <devcode@fb.com>
 2026-07-17 22:20:54 -07:00
Alison Shao a5c0b94034 Let CI server launches wait longer for ports held by a dying predecessor (#31281) 2026-07-17 21:45:24 -07:00
Elizaveta MartirosianElizaveta MartirosianElizaveta Martirosianronnie_zheng
 		44e4999ab2 [Diffusion] Use SGLang server for ERNIE-Image prompt enhancement (#31354) 
Co-authored-by: Elizaveta Martirosian <you@example.com>
Co-authored-by: Elizaveta Martirosian <elizaveta.martirosian@gmail.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
 2026-07-18 06:55:28 +03:00
R0CKSTAR 87dc211b87 [MUSA] Fix sglang-kernel build (#31634) 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
 2026-07-17 20:51:09 -07:00
xdtbynd 359009fa00 [Bugfix][NPU] Fix/Refactor routed scaling factor application in MoE routing (#31449) 2026-07-18 10:59:13 +08:00
DarkSharpnessClaude Fable 5BBufjessiewei7root
 		67e7f8d13a [JIT] Refactor dtype traits into DTypeTrait and unify warp reductions (#30838) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: BBuf <xiaoyu.zhang@radixark.ai>
Co-authored-by: jessiewei7 <jessiewei747@gmail.com>
Co-authored-by: root <root@GPUC5A6.maas>
 2026-07-18 10:07:18 +08:00
Brayden Zhong 238b2b2c9c Remove QServe and FBGEMM FP8 quantization (#31109) 2026-07-17 17:10:34 -07:00
Alison Shao f926c30c57 Revert "Fix mamba track-boundary seqlen under overlap scheduler (#31369)" (#31622) 2026-07-17 17:03:10 -07:00
Mick 42a058c760 optimize: avoid fla l2-norm recompilation by token count (#31558) 2026-07-18 07:58:36 +08:00
Qiaolin Yu 01a96720c6 [spec decoding] replace torch.multinomial with several native torch op in rejection sampling (#31620) 2026-07-17 16:58:11 -07:00
Baizhou Zhang 304a529558 Revert "Bump FlashInfer to 0.6.15 and revert regressions" (#31625) 2026-07-17 16:46:33 -07:00
Lianmin Zheng c95026aed3 Upgrade llguidance to 1.7.6 (#31484) 2026-07-17 16:31:44 -07:00
Qiaolin Yu 632adff9fd refactor logprob processor layer (#20071) 2026-07-17 16:28:10 -07:00
sglang-botandsglang-bot 0ad0ff2e9e chore: bump sglang-kernel version to 0.4.5 (#31618) 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
 2026-07-17 15:58:36 -07:00
Qiaolin Yu e2d2e8d07e [spec decoding] fix multi_layer_eagle rotate_input_ids kernel registration (#31614) 2026-07-17 15:18:01 -07:00
Sam (Kesen Li) ec6a3163b7 [Feature] Add FP4 KV Cache Design and support SM120 GPUs (#21601) 2026-07-17 14:49:43 -07:00
Brayden ZhongandBrayden Zhong 7fc3fb9657 Remove deprecated Mamba flags from doc, wrong FP8 GEMM docstrings and change Nemotron image to 0.5.15 (#31094) 
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
 2026-07-17 14:34:29 -07:00
Liangsheng Yin 2c856abbe3 [Fix] Enable chunked input-logprob processing by default to cap peak memory (#31498) 2026-07-17 13:19:03 -07:00
Andy Ye d389039337 [diffusion] Opt in Qwen and Wan multi-output conditioning expansion (#31233) 2026-07-17 12:00:23 -07:00
fanxingranandkk fec6131844 [AMD] Disable DSA fused top-k v2 on ROCm for GLM-5.x / DeepSeek-V3.2 (#30506) 
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
 2026-07-17 10:22:14 -07:00
Muhammad Safiullah MemonandMuhammad Safiullah 2db21daf8d Fix Heartbeat Checker in KV Manager Disaggregation (#31584) 
Co-authored-by: Muhammad Safiullah <muhammadsafiullah136@gmail.com>
 2026-07-18 01:21:50 +08:00
Zhaoyi LiandMichael 2c64b7782e [AMD][PD] Fix early-send cached-prefix KV racing the prefill forward on mori (#31368) 
Co-authored-by: Michael <13900043+michaelzhang-ai@users.noreply.github.com>
 2026-07-17 10:08:04 -07:00
NOOBandR0CKSTAR 5e7eed4c00 [MLX] Honor --max-running-requests in the model runner stub (#30547) 
Co-authored-by: R0CKSTAR <yeahdongcn@gmail.com>
 2026-07-17 08:24:00 -07:00
Mick 681c223570 refactor: wrap split backends once on full-attention backends (#31439) 2026-07-17 19:15:04 +08:00
Mick 24a8944e15 fix: enable Kimi multimodal breakable prefill cuda graph replay (#31391) 2026-07-17 19:13:54 +08:00
DarkSharpnessClaude Fable 5root
 		132ade55cd [Kernel] Rewrite JIT custom all-reduce (v2) with a decoupled kernel/storage design (#31049) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: root <root@GPUC5A6.maas>
 2026-07-17 18:37:22 +08:00
Liangsheng Yin 19f4859b30 [CI] Exclude current process memory from GPU idle check (#31571) 2026-07-17 02:11:41 -07:00
Mohammad Miadh AngkadandBrayden Zhong d67aa05697 Bump FlashInfer to 0.6.15 and revert regressions (#31502) 
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
 2026-07-17 00:50:12 -07:00
huangtingweiandZhangheng 44e3dd2713 [HiCache] Optimize HiCache host pool free-list release (#30658) 
Co-authored-by: Zhangheng <hzh0425@apache.org>
 2026-07-17 14:52:08 +08:00
Liangsheng Yin 6e3be088a9 [Spec] Allocate the verify tree-mask scratch on the target backend only (#31527) 2026-07-16 23:23:21 -07:00
Junlin Wu bbd2a3fe4a ✨ [llm][npu][quant] Add W4A4 MXFP4 quantization support for Qwen3 Dense on Ascend NPU (#23795) 2026-07-17 09:06:30 +03:00
Xiaoyu ZhangandClaude Opus 4.8 1ac1ffea0c [Kernel] Fill non-CUDA coverage: HIP (aiter/rocm-triton) + Ascend NPU backends (RFC #29630) (#31307) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-17 14:05:35 +08:00
Khoa PhamandCursor 96dd96c02b [DCP] Auto-disable tc_piecewise and breakable prefill CUDA graphs under DCP (#31532) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-16 22:17:50 -07:00
Khoa Phamandkpham-sgl d310fce85f [Fix] Update PR #25015 revert for fused topk=1 draft postprocess (#31519) 
Co-authored-by: kpham-sgl <kpham-sgl@users.noreply.github.com>
 2026-07-16 21:51:16 -07:00
Khoa Phamandkpham-sgl ead703815e [DCP] Enable decode context parallel for Kimi K2.5 NVFP4 (#31514) 
Co-authored-by: kpham-sgl <kpham-sgl@users.noreply.github.com>
 2026-07-16 21:50:42 -07:00
AuFlowandAuFlow bf417440e9 [Scheduler] Add SGLANG_MAX_NEW_TOKENS_LIMIT to cap per-request max_new_tokens (#22591) 
Co-authored-by: AuFlow <AuFlow@users.noreply.github.com>
 2026-07-16 21:34:10 -07:00
Liangsheng Yin 45824c69ca fa3: build the topk>1 verify replay page table on-device (#31381) 2026-07-16 21:21:01 -07:00
Liangsheng Yin 27ad9d11b1 [CI] Wait for GPU memory release before each test class setUpClass (#31509) 2026-07-16 21:06:29 -07:00
Peng Xingchen 12af7e6c34 [NPU] Fix DSA top-k seed buffer shape for MTP IndexShare (#31005) 2026-07-17 12:05:57 +08:00