minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
18,518 Commits 2 Branches 0 Tags
d903351a669dcda7742821af83ebc0ce99f674f5
Commit Graph
12882 Commits
Author SHA1 Message Date
Baizhou ZhangandChunan Zeng 5ebb16005d [DeepSeek-V4.1] Bump FlashMLA to the fork's rebase head (v4.1 kernels) (#39171) 
Co-authored-by: Chunan Zeng <zcnrex@gmail.com>
 2026-09-13 15:43:19 -07:00
Shuwen Wang ff228d11fe [HiCache] Release buffer prefetch anchor locks during storage cleanup (#38483) 2026-09-13 20:47:21 +00:00
Shuwen WangandClaude Opus 5 7f1f8c706a [mem_cache][10/N] refactor: drop the redundant _component suffix in unified_cache/components (#35644) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-09-13 21:38:20 +08:00
Shangming CaiandXinyuan Tong 14a131ad5b [PD][OpenAI] Gate /v1/responses persistence behind --enable-response-store, default off (#39122) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2026-09-13 21:20:47 +08:00
MickMick QianClaude Opus 5
 		f9fca05803 [diffusion] fix: make the sp sequence gather pass contiguous shards (#39291) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-13 20:30:52 +08:00
MickMick QianClaude Opus 5
 		9ffe548738 [diffusion] fix: don't route an unreadable checkpoint into the native fallback (#39292) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-13 20:30:24 +08:00
Jundong LiuandShuwen Wang 7078e5ffbc [HiCache] Publish a host store event for storage-prefetch refills (#38486) 
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
 2026-09-13 10:29:14 +00:00
huangtingweiandhzh0425 a7cf4a6fbc [Unified Cache][7/N] Support MTP, EAGLE, and DSpark draft KV caches in the external linker (#37914) 
Co-authored-by: hzh0425 <hzh0425@apache.org>
 2026-09-13 18:22:06 +08:00
Jimmy ShongClaude Fable 5.1rdxaYangmin LiManriqueyhyang201
 		cebca698e2 [Qwen3.8] Enable NVIDIA NVFP4 on DGX Spark with file-backed PLE and PDL router fix (#39126) 
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: rdxa <rdxa@rdxa-int-spark-01.yvb.moe>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Manrique <nanomlm@gmail.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
 2026-09-13 16:23:41 +08:00
jacky.chengandHAI d6fabb74b4 [AMD][Fix] Fix aiter bpreshuffle GEMM for output sizes it cannot dispatch for qwen3.5 mxfp-attn-fp8-v2 TP4 (#37564) 
Co-authored-by: HAI <hixiao@gmail.com>
 2026-09-12 23:11:44 -07:00
MickMick QianClaude Opus 5
 		492f346d88 [diffusion] CI: set an explicit x264 preset for video output (#38657) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-13 13:47:41 +08:00
William HuandXinyuan Tong 6d6d42d1c0 [Fix] Preserve GLM tool argument types across JSON Schema unions (#39136) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2026-09-13 13:47:13 +08:00
Byron HsuByron HsuManik Singhal
 		34b2904741 [Session] Work with PD and Fix empty continuations (#39038) 
Co-authored-by: Byron Hsu <byron+per@periodiclabs.ai>
Co-authored-by: Manik Singhal <3400497+Manikvsin@users.noreply.github.com>
 2026-09-12 22:24:32 -07:00
cctry 24b6c1c7f5 Fix multimodal embedding cache retaining full batches through views (#39120) 2026-09-12 21:37:14 -07:00
cctryandcctry 7e3d18bbcc Add a provider hook for prefill-buffer ceilings (#39182) 
Co-authored-by: cctry <17473714+cctry@users.noreply.github.com>
 2026-09-12 21:37:10 -07:00
cctryandcctry 206034e520 Keep graph-pool borrows on their allocation stream (#39180) 
Co-authored-by: cctry <17473714+cctry@users.noreply.github.com>
 2026-09-12 19:26:09 -07:00
cctryandcctry 18cc55dc0b Expose a capacity check for graph-pool borrows (#39178) 
Co-authored-by: cctry <17473714+cctry@users.noreply.github.com>
 2026-09-12 19:24:57 -07:00
Xiaoyu ZhangandMick Qian 23bc4c6ed9 [Diffusion] Return Qwen-Image-Layered outputs and preserve CFG2 rounding (#38549) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
 2026-09-13 09:15:47 +08:00
Xiaoyu ZhangandMick Qian 3e035a3513 [Diffusion] Optimize Qwen-Image-Edit attention on Hopper (#38584) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
 2026-09-13 09:15:01 +08:00
Cheng Wan fa663e7297 config: delete the redundant full stamp in initialize_model_parallel (#39202) 2026-09-12 17:27:21 -07:00
Cheng Wan fa260f26da config: delete dead ensure_model_parallel_initialized (#39137) 2026-09-12 17:27:12 -07:00
Cheng Wan 6804eeaabe config: an out-of-tree replacement point for every resolution-pipeline step (#39134) 2026-09-12 17:26:54 -07:00
xiaobochen-amdJohnQinAMDRuibinCheungZhang, Jiejing
 		6657f7d844 [MoE][ROCm] Admit the unified Triton router on ROCm, including single-group routing (#38328) 
Co-authored-by: JohnQinAMD <yanyuan.qin@amd.com>
Co-authored-by: RuibinCheung <ruibzhan@amd.com>
Co-authored-by: Zhang, Jiejing <jiejing.zhang@amd.com>
 2026-09-12 16:21:28 -07:00
Baizhou ZhangXinyuan TongzRzRzRzRzRzRzRShijin Zhangzanes-ops
 		a66451c058 [GLM-5.3 Flash] Restore and enable KPool metadata fusion (#38845) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zRzRzRzRzRzRzR <Yuxuan.Zhang2@liverpool.ac.uk>
Co-authored-by: Shijin Zhang <75300765+Dovis01@users.noreply.github.com>
Co-authored-by: zanes-ops <zanes@nvidia.com>
 2026-09-12 16:01:11 -07:00
Xinyi Song 21289cfd50 [AMD] Fix Dspark accept length and reduce host bubble on DSV4 (#39116) 2026-09-12 15:21:43 -07:00
cctryandcctry 7ae4af8187 Scope graph-pool borrowing to the runtime and reduce fragmentation (#39177) 
Co-authored-by: cctry <17473714+cctry@users.noreply.github.com>
 2026-09-12 11:45:17 -07:00
cctryandcctry 2784a86062 Reuse live CUDA graph executables during dedup registration (#39176) 
Co-authored-by: cctry <17473714+cctry@users.noreply.github.com>
 2026-09-12 11:44:17 -07:00
Byron HsuByron HsuManik Singhal
 		25a5641cf2 [Session + MM] Fix text positions in session continuations (#39144) 
Co-authored-by: Byron Hsu <byron+per@periodiclabs.ai>
Co-authored-by: Manik Singhal <3400497+Manikvsin@users.noreply.github.com>
 2026-09-12 10:31:55 -07:00
jlqibmClaude Opus 4.8Xinyuan TongXinyuan Tong
 		ae1acf822d [GraniteMoE] Load split per-expert quantized MoE weights (#37679) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-09-12 23:10:20 +08:00
MickMick QianClaude Opus 5
 		7b89b95168 [diffusion] feat: pick the attention backend by measuring it (#38689) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-12 21:52:16 +08:00
MickandMick Qian dc3171c322 [diffusion] CI: remove mova ulysses two-gpu CI case (#39097) 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
 2026-09-12 21:48:04 +08:00
Shijin ZhangXinyuan TongXinyuan Tong
 		925e684a88 [Feat][Responses API] Support custom tools, encrypted reasoning replay, developer tier and model validation (#38690) 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-09-12 21:29:12 +08:00
desmond-intel 6dc7b3421b Inference Support Mamba 2 and 1 (#34556) 2026-09-12 20:51:18 +08:00
KunalandClaude Fable 5.1 fd32226706 Fix gpt-oss RunAI streamer weight ownership (#38908) 
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-12 20:21:59 +08:00
Shuwen Wang bd45cd50ca [Unified Tree] Port SWA Branching-Point Caching to the Rust TreeCore (#37584) 2026-09-12 18:37:57 +08:00
Yanbin JiangandShuwen Wang 0b415fa573 [HiCache][LoRA] Isolate storage pages by extra key (#38577) 
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
 2026-09-12 18:18:14 +08:00
Shuwen Wang b9cb96496d [Unified Tree] Preserve aux LRU recency when splitting nodes (#38482) 2026-09-12 18:17:38 +08:00
Qiaolin Yu 6953dae005 [Qwen 3.8 Next] Remove unused tokenwise QSA implementation and tests (#38960) 2026-09-12 01:32:01 -07:00
Tuan Nguyen Gia 7c195b9151 [AMD] Fix Quark load of MiniMax-M3 MXFP4 index_qkv_proj (#37254) 2026-09-12 00:50:41 -07:00
MickandClaude Opus 5 bf3305b65e [diffusion] feat: read mapped layers directly when the host cannot cache them (#39022) 
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-12 15:48:03 +08:00
Xiaoyu ZhangandCursor 0a57403468 [Perf] Optimize Qwen3-VL unique-image serving on H100 (#36411) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-12 15:16:59 +08:00
Khoa PhamandClaude Fable 5.1 6ba96d329f [DCP] Resolve --dcp-comm-backend to fi_a2a/a2a by default for every model (#39165) 
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-11 23:48:42 -07:00
Shangming CaiandClaude Fable 5 981b947568 [Fix] Seed raw tokenizer_path for smg-grpc-servicer in gRPC mode (#39105) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-09-12 14:41:15 +08:00
ehuaa 1cdc5bca5e fix(qsa): clamp the compress gather to the rows this forward has (#38346) 2026-09-11 23:24:17 -07:00
YAMY 55e5e21c88 [Qwen3.8-Next] Add PD state transfer for Flash Next (#36651) 2026-09-11 22:31:45 -07:00
Ziang Li dbd4302bbb Keep NVFP4 blockscale swizzle padding on the input device (#39141) 2026-09-11 22:18:02 -07:00
Aurick Qiao c389dd0863 Fix RunAI object-storage checkpoint index filtering (#38988) 2026-09-12 12:25:57 +08:00
iridiumine a984c78330 [NPU] Support DFlash speculative decoding for MiMo-V2.5-Pro (mxfp4) (#37565) 2026-09-12 11:59:23 +08:00
Kevin MiClaude Fable 5.1Haocheng XiMick
 		ff1ce11348 [diffusion] model: support VDN-H3 with a hybrid_window_attn_h3 backend (#37903) 
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Haocheng Xi <xihc@berkeley.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-09-12 11:36:32 +08:00
FrancisandQiaolin-Yu e91c948057 feat: support TP>1 Domino rollout for DFlash V2 (#37069) 
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
 2026-09-11 18:51:11 -07:00