minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
18,694 Commits 3 Branches 0 Tags
dsv41-pd
Commit Graph
5089 Commits
Author SHA1 Message Date
Lianmin Zheng c95026aed3 Upgrade llguidance to 1.7.6 (#31484) 2026-07-17 16:31:44 -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
Liangsheng Yin 2c856abbe3 [Fix] Enable chunked input-logprob processing by default to cap peak memory (#31498) 2026-07-17 13:19:03 -07:00
Bingxu Chen 53229e88da [AMD] Fix stale imports in test_fused_fp8_kv_write.py (#31515) 2026-07-17 09:03:44 -07:00
Michael c546afc147 [AMD] Register 2 CPU/triton unit + kernel tests for AMD 1-GPU PR CI (#31379) 2026-07-17 09:01:46 -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
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
Baizhou Zhang e835512303 Add nightly test for GLM5.2 LayerSplit (#31512) 2026-07-17 00:29:14 -07:00
Xiaoyu ZhangandClaude Opus 4.8 619609aa5a [Kernel] Simplify sglang.kernels tests to idiomatic pytest style (RFC #29630) (#31546) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-17 15:06:26 +08:00
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
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
NOOB 444bbd866d [CI] Fix invalid suite name breaking all PR test lanes (#31539) 2026-07-16 22:30:05 -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
Ma Mingfei 486a56be56 [CPU] improve silu performance by replacing fp32 div with rcp14 (#31304) 2026-07-17 12:02:37 +08:00
Xiaoyu ZhangandClaude Opus 4.8 8432eafd3d [Kernel] Decouple KernelBackend from device + device-based CapabilityRequirement (RFC #29630) (#31292) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-17 10:35:34 +08:00
Polisetty V R K Jyothendra VarmaandRahul Vijayaraghavan 37f94cb7a0 [Intel GPU] DeepSeek V4 13/N: use sgl-kernel implementation of kernels in V2 Compressor to run on XPU (#28439) 
Signed-off-by: P V R K Jyothendra Varma <polisettyvarma@gmail.com>
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Rahul Vijayaraghavan <rahul.vijayaraghavan@intel.com>
 2026-07-17 09:16:04 +08:00
Kaixi dc0b3eb68f [2/3] [EAGLE] perf: Fuse TP vocab-parallel embedding (#30948) 2026-07-16 15:57:51 -07:00
Kaixi d539bf2cda [1/3] [EAGLE] perf: Fuse topk=1 draft postprocess (#30947) 2026-07-16 15:57:27 -07:00
Yoray Zack 77d23a796e [1/N] elastic-ep: Add runtime EP scale-up (#30164) 2026-07-16 15:53:44 -07:00
Liangsheng Yin 640101da13 [Fix] Deflake score engine determinism tests (#31494) 2026-07-16 15:42:47 -07:00
Bob ChenandZhiqiang Xie 7cd55c6818 [HiCache] Optimize L2 mem allocation when cache miss in L3 (#19320) 
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
 2026-07-16 15:00:53 -07:00
Liangsheng Yin fc1e3797b7 [Spec] Split the capture width from num_tokens_per_req and gate replay on it (#31255) 2026-07-16 14:59:11 -07:00
Serge Panev 1f34911de7 [NemotronH] Load shared embed_tokens/lm_head in MTP draft weights (#30456) 2026-07-16 17:20:38 +00:00
pllimax 4ad418d2c3 Push test case scripts from test repo to main upstream community repository (#31114) 2026-07-16 21:24:01 +08:00
Mick 7d0fd5101d optimization: shard kimi dp image feature transport and misc optimizations (#31227) 2026-07-16 20:31:42 +08:00
jojoandhzh0425 b296e1a503 [hicache]: add mamba concurrency io transfer kernel (#30535) 
Co-authored-by: hzh0425 <hzh0425@apache.org>
 2026-07-16 18:13:02 +08:00
Wang, FangYuan e2d021d4ab [AMD] Support two batch overlap with MTP on DeepSeekV4 (#30238) 2026-07-16 02:34:04 -07:00
Brayden ZhongrootBrayden Zhong
 		e5f9804e26 Refining fused A GEMM dispatch (#31241) 
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
 2026-07-16 16:57:01 +08:00
Yuan Luoandluoyuan.luo a798a2aeea [GDN/KDA] Fuse SM100 CuteDSL prefill state I/O into the chunk h kernel (#30169) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-07-16 16:40:33 +08:00
hjzhanghjzhanghnyls2002
 		db7e6807de [BugFix] Preserve tokenizer worker fanout when skip_tokenizer_init is enabled (#30682) 
Co-authored-by: hjzhang <zhanghjzzz@qq.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
 2026-07-16 01:29:46 -07:00
zhengyao 01b003255a [AMD]Reuse fused FP8 KV cache write on standard aiter prefill/decode (#26852) 2026-07-16 01:05:04 -07:00
Ethan ZHUClaude Opus 4.7vuuihcZhiqiang Xie
 		095a817612 [Bugfix][HiCache] measure load-back duration with CUDA events (#26411) 
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: vuuihc <vuuihc@users.noreply.github.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
 2026-07-16 00:11:04 -07:00
Xiaoyu Zhang e73f323464 [JIT] Reduce MoE fused gate CI test sweep (#31400) 2026-07-16 14:42:45 +08:00
Ryan Zzzandzhujunyu 5af65d8542 [DeepSeek-V4] Support BF16 Compress State for Online C128 (#29609) 
Co-authored-by: zhujunyu <zhujunyu.666@bytedance.com>
 2026-07-15 23:17:29 -07:00
guzekai01 dee91c51cf perf(deepseek_v4): enable SGLANG_OPT_FP8_WO_A_GEMM on sm90 (Hopper) (#28983) 2026-07-16 11:16:32 +08:00
Mick d9003dd452 fix: skip unsafe automatic prefill graph capture (#31204) 2026-07-16 09:27:38 +08:00
Brayden ZhongandBrayden Zhong 7647a9d260 Fuse the preprocess kernels of trtllm-gen attention (#29690) 
Co-authored-by: Brayden Zhong <brayden.zhong@radixark.ai>
 2026-07-15 18:21:34 -07:00
Po-Han Huang (NVIDIA) 5d004a20c5 Fix FlashInfer A2A top-k ID dtype (#29929) 2026-07-15 17:56:11 -07:00
Liangsheng Yin b0b2dfbda1 [Spec] Extract the shared draft() tail into build_eagle_verify_input (#31375) 2026-07-15 15:59:31 -07:00
Yuzhen ZhouClaude Fable 5hnyls2002
 		7a973c03a0 [Bugfix] Stamp capture-time num_tokens_per_req in multi-layer EAGLE; close jit_kernel CI filter gaps (#31367) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
 2026-07-15 15:24:32 -07:00
Jorge António 26cb0fcdda Empty _REQ_TYPES_WITH_OPAQUE_FIELDS on the msgpack IPC path (#29465 Task 4) (#30182) 2026-07-15 14:55:06 -07:00
Michael 67148447a6 [AMD] Register 3 CPU-bound / triton unit + light-integration tests for AMD 1-GPU PR CI (#31088) 2026-07-15 14:36:05 -07:00
karverma-amd ec32590025 feat(moriep): add fp4 combine dtype (SGLANG_MORI_COMBINE_DTYPE=fp4) (#30706) 2026-07-15 14:21:41 -07:00
jacky.cheng e78051a419 [AMD] [Fix] Fix --attention-backend triton work for DeepSeek MLA on MI355 (null-K + decode dispatch + RoPE) (#30355) 2026-07-15 14:19:23 -07:00
Liangsheng Yin e76cc75cfa [CI] Remove nightly registrations redundant with scheduled stage runs (#31371) 2026-07-15 14:12:07 -07:00
Mohammad Miadh Angkad 18043aec20 [CI] Fix TRTLLM MHA graph metadata test fixture (#31332) 2026-07-15 12:44:51 -07:00
YAMYandXuwei Li 2d00e20a52 [Disagg][Qwen3.5] Fix heterogeneous attn-TP scatter transfer: GDN conv sub-block slice + GQA replicated-KV head map (#30997) 
Co-authored-by: Xuwei Li <lixuwei.xy@gmail.com>
 2026-07-16 02:31:37 +08:00