minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
18,675 Commits 4 Branches 0 Tags
main
Commit Graph
18675 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Thomas Wang d15a2dc72c [AMD] dpsk-v4 swa loc cache support (#26931) 2026-06-01 22:37:07 -07:00
kkwunhuangBingxu Chen
 		4226a6f13a [AMD] Fix GPT-OSS MXFP4 accuracy on ROCm AITER path (#26884) 
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: Bingxu Chen <bingxche@amd.com>
 2026-06-01 22:30:43 -07:00
Khoa PhamandCursor 08526c7fca [Spec] FrozenKVMTP fold assistant seed into captured draft graph (#25539) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-01 22:27:25 -07:00
Kurkur f27fa0da93 [NPU][Docs] Kimi-K2.5 best practice (#26774) 2026-06-02 13:14:14 +08:00
shuwenn f40b2ca9d3 chore(CODEOWNERS): add allocator/ owners and @alphabetc1 to mem_cache (#27003) 2026-06-01 22:07:15 -07:00
Ethan ZHUandZhangheng 594ec6335d [Bug Fix][HiCache] Drop @lru_cache on UnifiedTreeNode.get_prefix_hash_values (#26939) 
Co-authored-by: Zhangheng <hzh0425@apache.org>
 2026-06-02 12:38:28 +08:00
ThanhhaoHao PhanZijie XiaClaude Opus 4.8
 		1c0019da75 [Docs] GLM-4.7 cookbook: add NVIDIA Blackwell (B200, GB200) + NVFP4 sections (#26384) 
Co-authored-by: Hao Phan <htphan@nvidia.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-01 20:47:51 -07:00
popsiclexuandpopsiclexu 951fa05a09 [MoE] Support BF16 standard A2A with DeepGEMM runner (#26473) 
Co-authored-by: popsiclexu <zhenxue.xu@mthreads.com>
 2026-06-01 20:40:38 -07:00
Teng MaandZijie Xia b562da0d9f [PD] docs: clarify disaggregation IB device formats (#25521) 
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
 2026-06-02 11:38:33 +08:00
ybyang 9fe8b72912 Speed up DeepGEMM JIT warmup with per-PP-rank parallel compile (#26567) 2026-06-01 19:51:27 -07:00
Shu WangYangmin LiClaude Opus 4.7
 		0574d2b8a5 [NVIDIA] [GDN] Enable FlashInfer MTP verify on SM100+ (Blackwell) (#23273) 
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-06-01 18:56:42 -07:00
Liangsheng Yin 54143264bf ci: disable cross-job fast-fail for run_all_tests dispatch (#26990) 2026-06-01 18:32:41 -07:00
Prabhu Prakash KagithaClaude Sonnet 4.6zijiexiaZijie Xia
 		98a1b58c47 docs(cookbook): port popular model usage guides into cookbook pages (#25813) 
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
 2026-06-01 17:41:49 -07:00
Liangsheng Yin 5e63200064 ci: full parallelism for run_all_tests dispatch (#26986) 2026-06-01 17:40:43 -07:00
Liangsheng Yin f6d0beaca8 Revert "Support spec v2 tree drafting (eagle topk>1) with page_size==1" (#26981) 2026-06-01 17:16:44 -07:00
Glen Liu 167272e785 [LoRA] add lora chunked req test and fix (#23179) 2026-06-01 16:25:27 -07:00
chenkaiyueandZhiqiang Xie dff45411da [HiCache] Prevent KV cache data loss when radix tree node is split b… (#16946) 
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
 2026-06-01 15:58:06 -07:00
Qiaolin Yu 4151a04d1a [Perf][Spec Decoding] Skip cat/topk/sort/gather in draft_forward for topk=1 (#26424) 2026-06-01 15:37:47 -07:00
Liangsheng Yin 1d4ee060c2 Support spec v2 tree drafting (eagle topk>1) with page_size==1 (#26866) 2026-06-01 15:37:20 -07:00
Baizhou Zhang 2fdae94e46 docs: update RTX PRO 6000 deployment snippet (#26968) 2026-06-01 14:34:27 -07:00
Yongfei Xu 5700790c05 DeepSeek V4: Support context parallelism with fused MoE (non-DeepEP) (#24947) 2026-06-01 14:25:43 -07:00
Qiaolin Yu 3bce192bd2 [misc] update adaptive spec decoding code owners (#26965) 2026-06-01 14:08:09 -07:00
eeechoandClaude Opus 4.6 524ba10eda feat: SM120 (Blackwell Desktop) support for DeepSeek-V4 inference (#24692) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-06-01 14:05:20 -07:00
Liangsheng Yin dfa1af99f5 Fix kill_process_tree reap wait crashing on pidfd EINVAL (#26964) 2026-06-01 13:56:59 -07:00
shuwennClaude Opus 4.7Jarrod Barnes
 		a0670b5ba3 [SPEC] feat: add adaptive speculative decoding metrics (#25940) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Jarrod Barnes <jbarnes850@gmail.com>
 2026-06-01 13:53:30 -07:00
Shu Wangandzijiexia 106092123f Update Qwen3-Coder docs_new NVIDIA guidance (#24435) 
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
 2026-06-01 13:38:34 -07:00
Khoa Pham da01f2974e [Log] include max_token_num and hidden_dim in FlashInfer workspace init log (#26605) 2026-06-01 13:26:52 -07:00
Mick f2beb7bc76 [diffusion] improve: avoid cosmos3 cpu float video postprocess (#26956) 2026-06-02 04:12:01 +08:00
Khoa PhamandClaude Opus 4.8 cb8a103b81 chore: add @pyc96 as codeowner for FrozenKVMTP module (#26953) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-01 13:06:58 -07:00
Mick 9a8ab2d22b [diffusion] fix: align cosmos3 text packing with official pipeline (#26950) 2026-06-02 02:07:17 +08:00
Kris HungClaude Opus 4.7ishandhanani
 		86afa21ca7 feat: optional caller-supplied mm_hashes on GenerateReqInput (#25300) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
 2026-06-01 20:04:37 +02:00
Byron HsuByron HsurootCursorMick
 		f6a5a1b59c [RL+VLM] Avoid retokenization drift for pre-tokenized (token-id) VLM requests (#26555) 
Co-authored-by: Byron Hsu <byron+per@periodiclabs.ai>
Co-authored-by: root <root@slurm-h200-209-231.slurm-compute.tenant-slurm.svc.cluster.local>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-06-01 09:58:14 -07:00
Mick 1988a2c9ea [diffusion] feat: improve cosmos3 serve API support (#26926) 2026-06-02 00:53:39 +08:00
Mick ed24e3aae8 [diffusion] feat: speed up png image output saving (#26947) 2026-06-02 00:43:02 +08:00
Ke Bao f59bbef841 Split SWA leaf to one window on insert (#26919) 2026-06-01 23:46:55 +08:00
Lukas HumbelandClaude Opus 4.7 d8a5a25c36 Refactor NIXL hicache. Add O_DIRECT support (#25173) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-06-01 17:28:53 +02:00
Yiqi YangYiqi YangClaude Opus 4.7
 		89feb18eb9 [diffusion] feat: allow --dit-cpu-offload with --dit-layerwise-offload (#26925) 
Co-authored-by: Yiqi Yang <yiqi.yang@kiwiar.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
 2026-06-01 23:17:53 +08:00
Ke Bao 693adabff7 Fix Mamba2Metadata dropping has_mamba_track_mask (#26877) 2026-06-01 22:03:59 +08:00
zhaozx-cn fd16e05252 [NPU] fix npu profiler (#24835) 2026-06-01 21:44:24 +08:00
Bi Xue 6965fe0eec [sgl] Window-aware LRU refresh for SWA prefix cache in unified cache (#26615) 2026-06-01 19:35:18 +08:00
Chi McIsaac 931765e23e Do not cap DeepSeek V4 PD prefill by SWA pool size (#26607) 2026-06-01 19:29:45 +08:00
yiheng 1f8d3c7a42 [Speculative] [NPU] Adaptive-SD NPU support (#25644) 
Signed-off-by: EanWang211123 <wangyiheng@sangfor.com.cn>
 2026-06-01 19:19:58 +08:00
Liangsheng Yin 1bff7a290f Refactor EAGLE infer tests: shared fixture + kits + overlap matrix (#26871) 2026-06-01 03:55:01 -07:00
Bingxu ChenandClaude Opus 4.8 89410b380b [AMD] Pin compressed-tensors==0.15.0 to fix ROCm nightly build (#26879) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-01 17:33:00 +08:00
giang_ng_tr 2394dede0e [EPD][Perf] Async image preprocessing and cross-request ViT batching for encode_server (#25669) 2026-06-01 16:52:12 +08:00
Yuan Luoandluoyuan.luo bc36231d65 [KDA] Support KDA packed decode (#26586) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-06-01 16:52:01 +08:00
amote-i d078cb72bd [NPU] [DOC] clarify Ascend NPU exclusive supported values for speculative args (#26903) 2026-06-01 16:40:11 +08:00
YC Yen-Ching TsengCursor AgentBingxu ChenBingxu Chen
 		b14fba17d9 [AMD] make bypass-fastfail label also disable within-suite fast-fail (#26909) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
Co-authored-by: Bingxu Chen <bingxche@amd.com>
 2026-06-01 16:17:59 +08:00
Ke Bao cdd06011a1 Make unified tree SWA hicache tests faithful to write-through backup (#26870) 2026-06-01 16:08:57 +08:00
Mengxuan Xiong ff642ed936 [MoE] Extend kimi_k2_moe_fused_gate to support 256 experts (MiMo V2 Flash) (#26303) 2026-06-01 16:03:58 +08:00