minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
18,694 Commits 4 Branches 0 Tags
dsv41-pd
Commit Graph
18694 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Xiaoyu Zhang 8524678889 Fix MiniMax MSA fallback when fmha plan is unavailable (#29250) 2026-06-26 23:14:31 +08:00
Xiaoyu Zhang 18b0e5757e [Diffusion] Fuse LTX2 Ada values (#29390) 2026-06-26 23:13:15 +08:00
Aleksi Vesanto b91348071e [diffusion] optimize: shard qwen text embed in sp (#29147) 2026-06-26 21:44:45 +08:00
Xinyu JiangZhiyao Jiangbingxche
 		b73e57210a [AMD CI] Add nightly Miles ROCm 7.2 MI350X suites (#28853) 
Co-authored-by: Zhiyao Jiang <jessicajiang324@gmail.com>
Co-authored-by: bingxche <bingxche@amd.com>
 2026-06-26 18:47:00 +08:00
syy-hw f5708c3f91 [NPU] Fix mllama cross-attention crash in ascend extend SDPA (#29374) 2026-06-26 17:13:17 +08:00
Yan Ru Pei c0d4d1897c fix: batch BlockRemoved events per radix node (#29265) 2026-06-26 16:13:40 +08:00
zijiexiaandClaude Opus 4.8 c21c2d9421 [Docs] Cookbook: match playground docker image resolution to deployment (hw|quant) (#29400) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-26 00:56:34 -07:00
Khoa PhamCursorClaude Opus 4.8
 		999199f9ff [DeepSeek V3] Run routed experts on main stream in dual-stream MoE (#29142) 
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-26 00:48:59 -07:00
WenhaoZhangniehen61741639206518@qq.com
 		aeb4e98108 [diffusion] model: support JoyEcho multi-shot A/V generation support (#27420) 
Co-authored-by: niehen6174 <niehen6174@users.noreply.github.com>
Co-authored-by: 1639206518@qq.com <niehen6174>
 2026-06-26 15:46:31 +08:00
zijiexiaandClaude Opus 4.8 dd56a9f069 [Docs] Add NVFP4 quantization to GLM-5.2 cookbook (#29380) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-26 00:40:13 -07:00
Xiaoyu ZhangandClaude Opus 4.8 5996b54bd3 [KDA-Pilot] Add diffusion causal Conv3D cat-pad CUDA fast path for Cosmos3 (#29281) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-26 15:06:49 +08:00
Yuan Luoandluoyuan.luo a10a24e9a7 [GDN][KDA] ReplaySSM buffered output-only decode for Linear Attention (#28451) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-06-26 14:17:02 +08:00
Polisetty V R K Jyothendra VarmaandMa Mingfei dc113e8804 [Intel GPU] DeepSeek V4 3/N: Support hc_split_sinkhorn on XPU using sgl_kernel (#27783) 
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-06-26 13:57:13 +08:00
Khoa PhamandCursor eeee3abbbf [CI] Fix false spec accept length failure after profiling phase (#29329) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-25 22:19:30 -07:00
ziang663 ff89e0fe9a Fix KV event publisher bind conflict under PP (#29044) 2026-06-26 12:50:49 +08:00
ziang663 8fd6e9e017 Fix fixed-size HiCache capacity under PP (#29258) 2026-06-26 12:49:23 +08:00
Liangsheng Yin b6ebdcc92e [test] Split perf table out of fwd occupancy kit report (#29348) 2026-06-25 20:23:42 -07:00
jianzhao-xu cc294829aa [NPU] fix best practicce docs (#29303) 2026-06-26 11:17:50 +08:00
Xinyuan Tong 30ea4c0f4b build(sgl-kernel): bump FlashMLA pin + fix cccl include for CUDA 13 (#29067) 2026-06-25 20:00:15 -07:00
Raiden MakotoandRaiden-Makoto 7f376644e0 [AMD] [GLM5] Mark EAGLE verified on MI300X/MI325X (gfx942) in GLM-5.1 cookbook (#29313) 
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
 2026-06-26 10:49:58 +08:00
Zhaoyi LiMichaelbingxcheyctseng0211
 		413aeac0c9 [AMD][DI][CI] 1/N: MI355X disaggregation nightly benchmark (#29084) 
Co-authored-by: Michael <13900043+michaelzhang-ai@users.noreply.github.com>
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: yctseng0211 <yctseng@amd.com>
 2026-06-25 19:21:28 -07:00
Wang, MengniPeng ZhangMa MingfeiWeiwei
 		cfc0a0e0e0 Add Intel Quantization Support in SGLang (#18139) 
Signed-off-by: Mengni Wang <mengni.wang@intel.com>
Signed-off-by: WeiweiZhang1 <weiwei1.zhang@intel.com>
Co-authored-by: Peng Zhang <aniz1905@gmail.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
Co-authored-by: Weiwei <weiwei1.zhang@intel.com>
 2026-06-26 09:54:35 +08:00
amote-i 10ff3c1dcb [NPU] [DOC] Add environment prerequisites to model tutorials (#29293) 2026-06-26 09:51:06 +08:00
Khoa PhamandClaude Opus 4.7 6c92f9f328 fix(bench): pass DCP_RANK/DCP_WORLD_SIZE to set_mla_kv_buffer_kernel (#29356) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-06-25 18:13:57 -07:00
hhhh1252023 781537b61d [NPU] Nightly CI refactor and enhancement (#27433) 2026-06-26 08:52:06 +08:00
Yi Zhong f83cbc2516 Add LFM2.5-230M to the LFM2.5 cookbook (#29321) 2026-06-26 08:27:57 +08:00
Yibo Cai 4b0b0ea55f [sgl-kernel/cpu]: exclude amx gemm source from arm build (#29286) 2026-06-26 08:23:43 +08:00
Xinyuan Tong ed71fb8f95 fix(anthropic): detect-and-passthrough mid-conversation system messages (#28906) 2026-06-25 17:14:12 -07:00
Yibo Cai 4ce1c180bd [sgl-kernel/cpu]: fix arm64 w8a8 moe kernel signature (#29270) 2026-06-26 08:11:57 +08:00
Lijuan Tang 623300a589 [MLX] Fix FutureMap relay unit test to use RelayPayload (#29311) 2026-06-25 16:53:58 -07:00
R0CKSTAR 38e857f423 [MUSA][diffusion] Bump torchada version to 0.1.68 (#29236) 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
 2026-06-25 16:53:43 -07:00
Ma Mingfei 1ba7c79761 [CPU] add indices in chunk_gated_delta_rule (#29267) 2026-06-26 07:51:07 +08:00
Khoa PhamandClaude Opus 4.7 c8c6757bed test(dp-attn): drop --enable-torch-compile from TestDPAttentionDP2TP2 (#29345) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-06-25 16:41:35 -07:00
Yueming Yuan 65f31acc6c Add yueming-yuan to CI_PERMISSIONS.json (#29341) 2026-06-25 16:18:54 -07:00
Augusto Yao ea8f4e9f3f [feature] implement dcp for deepseek_v2 (#14194) 2026-06-25 15:15:04 -07:00
Liangsheng Yin e4696ed62d [test] Report token tps in fwd occupancy kit and force ignore_eos (#29332) 2026-06-25 15:08:33 -07:00
kkandwunhuang b7d3c3016d [AMD] Feat/dsv4 aiter reduce scatter decode (#29103) 
Co-authored-by: wunhuang <wunhuang@amd.com>
 2026-06-25 13:45:18 -07:00
Mohammad Miadh Angkad 212c30d008 [MoE Refactor] Centralize FlashInfer CUTLASS MoE runner (#28211) 2026-06-25 13:40:33 -07:00
cctry dbe9e3b706 [PD] Early-send cached-prefix KV overlapping uncached prefill forward (#29316) 2026-06-25 13:31:53 -07:00
Michael e6efe10072 [AMD] Register 5 JIT kernel unit tests for AMD nightly CI (#29197) 2026-06-25 13:12:58 -07:00
Lianmin Zheng 118d6b2e5e [Cleanup] Style and type annotation improvements extracted from #28688 (#29224) 2026-06-25 12:51:15 -07:00
Baizhou Zhang 3344b73c80 Add DeepSeek V4 Pro GB300 nightly and expand Kimi K25 nightly test (#28103) 2026-06-25 12:13:52 -07:00
weireweire f9a3720e2b Skip empty non-idle output batches (#28504) 2026-06-26 02:40:01 +08:00
Brayden ZhongandBrayden Zhong 9495737d82 Fix CI broken by #28450 (#29308) 
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
 2026-06-25 10:35:34 -07:00
Xiaoyu Zhang 4d06d4c97f Sync Gemma4 hardware table with Blackwell recipes (#29266) 2026-06-25 22:57:33 +08:00
Xiaoyu Zhangjingyu-mlClaude Opus 4.8
 		52c32035eb [diffusion] Add Qwen-Image ModelOpt NVFP4 support (#28928) 
Co-authored-by: jingyu-ml <jingyux@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-25 22:56:09 +08:00
Mick 890b38c211 [diffusion] doc: fix diffusion docs and cookbook drift (#29302) 2026-06-25 21:13:00 +08:00
YC Yen-Ching Tseng bc150173b2 [AMD] Fix stage-b-test-1-gpu-small-amd-nondeterministic timeout after VLM model swap (#29234) 2026-06-25 03:56:04 -07:00
Raiden MakotoandRaiden-Makoto 0075c8f02b [AMD] [GLM5] GLM-5.1 MXFP4 (MI355X) + enable EAGLE for gfx950 in cookbook (#29194) 
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
 2026-06-25 03:54:48 -07:00
Xiaoyu Zhang ddda4f9028 [Bugfix] Fix Ministral3 init argument forwarding (#29111) 2026-06-25 18:26:45 +08:00