kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-01 04:08:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,824 Commits 157 Branches 0 Tags
cfd49e233ceb94de3f702f70aef06e299836aede
Commit Graph

7855 Commits

Author SHA1 Message Date
JD
20d07c4384 Fix remote weight info nnode>1 and dp>1 (#17389) 2026-03-31 21:17:18 +08:00
Shangming Cai
ca2b2130ba [PD] Tiny cleanup after KVReceiver refactor (#21760) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2026-03-31 21:07:57 +08:00
Yuan Luo
c7adca9992 Fix kimi-linear launch server error (#21752) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-03-31 21:07:08 +08:00
Ke Bao
dbc97456ad Enable evict swa with piecewise cuda graph (#21754) 2026-03-31 20:07:16 +08:00
weireweire
4455d17619 [PD] Refactor Disagg Conn and Fix Hang with total_request/total_tokens Balancing (#21299) 
Co-authored-by: Weiliangl User <weiliangl@login-node.hosted.internal>
 2026-03-31 18:01:50 +08:00
R0CKSTAR
6c03ae6fe2 [diffusion] fix: fix typo (#21746) 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
 2026-03-31 17:51:46 +08:00
xiaoqi
a6a8b9b376 bugfix(model):fix deepstack index out of range error (#21727) 
Co-authored-by: xiaoqi.31 <xiaoqi.31@jd.com>
 2026-03-31 02:41:47 -07:00
Thomas Wang
5628e908ae [AMD] Use tgemm.mm for MoEGate router gemm in deepseek_v2.py (#21657) 2026-03-31 00:55:40 -07:00
xiazhahe
b4cb31f698 [NPU] fix conflict between empty_cache and use_mem_pool (#21507) 2026-03-31 15:37:33 +08:00
Mohammad Miadh Angkad
dd9c9c1b8e Add explicit disable flag for FlashInfer allreduce fusion (#21446) 2026-03-31 00:15:44 -07:00
Yuhao Yang
68a4573627 [diffusion] fix: fix Flux.2 with tp(#21664) 2026-03-31 14:14:59 +08:00
jacky.cheng
8ba992411d [AMD] Fix CI multimodal-gen-test-1-gpu-amd for gen model (#21621) 2026-03-30 23:02:20 -07:00
Jincong Chen
03e4f2858d [Perf]Remove H2D for Qwen3.5 SpecV2 (#20864) 2026-03-31 11:54:58 +08:00
Lewis
33e725b052 [Fix] Update supported custom_mem_pool types for mooncake (#21728) 
Co-authored-by: 百麒 <yaozhong.lyz@alibaba-inc.com>
 2026-03-31 11:18:30 +08:00
Xiaoyu Zhang
505eb312ec Revert "DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication" (#21719) 2026-03-31 10:22:01 +08:00
DarkSharpness
4e480982fa [misc] multiprocess compilation to speed up test (#21483) 2026-03-31 08:56:37 +08:00
kk
67c295b5f5 [AMD] fix performance regression issue when run gpt-oss with "--context-length 13824" (#21691) 2026-03-30 16:30:16 -07:00
Zhai Feiyue
daf697afda [AMD] Add SGLANG_DISAGGREGATION_NUM_PRE_ALLOCATE_REQS env var for configurable KV transfer overlap (#20410) 
Co-authored-by: HaiShaw <hixiao@gmail.com>
 2026-03-30 14:37:16 -07:00
Aditya Sharma
d6029de6ad [Bugfix][NPU] Skip FRACTAL_NZ format for MoE weights with unaligned dimensions (#21209) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
 2026-03-30 23:22:17 +03:00
Vedant V Jhaveri
4a9ffc3ab6 fix nemotron capture for non attention layers (#21436) 2026-03-30 12:50:49 -07:00
Yuxuan Zhang
ad064c2f4e [GLM-V and GLM-4.7] Cast to FP32 before gate projection for GLM model. (#21660) 2026-03-30 12:25:27 -07:00
Makcum888e
f4b0e9c64a [diffusion] [NPU] support ring attention on NPU with FA (#21383) 2026-03-30 20:10:55 +03:00
GXIN
752d260c77 [NPU][diffusion]: support parallel decoding of qwen-image (#20757) 
Co-authored-by: 高鑫 <gaoxin@gaoxindeMacBook-Pro.local>
 2026-03-30 20:03:24 +03:00
cen121212
ba6d54d0f0 [NPU] GLM-5 optimize with fused kernels (#18617) 2026-03-30 22:48:15 +08:00
xieminghe1
7119d59747 DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication (#14162) 
Co-authored-by: undefined <zhouchen.arrebol@jd.com>
 2026-03-30 22:27:28 +08:00
heziiop
673ffb3116 [NPU] fix eagle3 accept rate (#21255) 2026-03-30 21:58:25 +08:00
GXIN
c5c58c3349 [NPU][Diffusion] fix sp modulate for qwen-image-edit (#20974) 
Co-authored-by: 高鑫 <gaoxin@gaoxindeMacBook-Pro.local>
 2026-03-30 16:18:48 +03:00
Mick
0a1fb42869 [diffusion] CI: relax pr-test threshold (#21682) 2026-03-30 20:23:46 +08:00
Mick
b76730701b [diffusion] feat: enhance overlay mechanism (#21648) 2026-03-30 19:45:34 +08:00
LiYomi
1d6424d5ad fix: Mistral Small 4 fails to start due to config/weight format mismatch (#21620) 
Co-authored-by: mengxiancheng03 <mengxiancheng03@kuaishou.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 01:57:35 -07:00
strgrb
b246269444 fix mamba cache leak when adder fails to add a matched req. (#21404) 2026-03-30 16:45:49 +08:00
Baizhou Zhang
62a63eeff7 [Fix] Fix weight_loader property assignment for qwen3-next FP8 models (#21662) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 01:35:59 -07:00
Hubert Lu
e6071e60c0 [AMD] Support AMD MXFP4 Qwen3.5-397B-A17B model (#21234) 2026-03-30 01:14:18 -07:00
kk
b9a68c304e [AMD] Fused rope kv store (#21315) 
Co-authored-by: wunhuang <wunhuang@amd.com>
 2026-03-30 00:05:41 -07:00
blzheng
ed01e1d5d6 [CPU] add kernel apply_rotary_pos_emb_cpu for Qwen3-VL and Qwen3-Omni (#13121) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-03-29 23:43:46 -07:00
Aishwarya Ramasethu
c32ee48886 MFU metrics in Prometheus (#19395) 2026-03-29 23:40:06 -07:00
Polisetty V R K Jyothendra Varma
f0303fd07e [Intel GPU] Enable DeepSeek R1 inference on XPU (#18461) 
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
 2026-03-29 22:35:59 -07:00
Feng Su
9b4dd27478 [Fix] Fix Qwen3.5 MoE model loading and Mamba cache sharding in PP mode (#21448) 
Co-authored-by: zhangxiaolei123456 <zhangxiaolei.666@bytedance.com>
 2026-03-30 11:57:26 +08:00
Liangsheng Yin
c06ca1526c Fix circular reference in CustomTestCase.__init_subclass__ (#21650) 
Co-authored-by: wan4ch <wan4ch@gmail.com>
 2026-03-29 20:38:12 -07:00
Lianmin Zheng
9f7792415a Clean up TokenizerManager: remove dead code and improve rid validation (#21639) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-29 15:12:49 -07:00
Lianmin Zheng
f3970b17ef [Cleanup] Remove unused BatchMultimodalOutput and BatchMultimodalDecodeReq (#21640) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-29 14:54:25 -07:00
Lianmin Zheng
1d9c8e8c9e Simplify routed experts test and move base64 encoding to tokenizer manager (#21634) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-29 12:44:01 -07:00
Mohammad Miadh Angkad
2acdda1d85 [Fix] Remove redundant allreduce fusion block and skip TP=1 (#20621) 2026-03-29 12:30:40 -07:00
wili
bda94fc779 [Fix] SGLANG_USE_CUDA_IPC_TRANSPORT=1 and SGLANG_ENABLE_MM_SPLITTING=1 do not work at the same time. (#19915) 2026-03-30 01:15:26 +08:00
saatwiknagpal
d2440dcf58 [VLM] perf: optimize CUDA IPC for multimodal transfer by caching IPC pool handles (#21418) 2026-03-30 00:20:38 +08:00
wili
5bb9ca0e63 [Feature] Optimizations for JPEG input on NVIDIA GPU (#19749) 2026-03-30 00:06:14 +08:00
Bi Xue
42c46e6334 [sgl] disable piecewise cuda graph when a model doesn't have layers (#21565) 2026-03-29 23:04:20 +08:00
Hanlin Bi
aa9177152e fix cuda graph capturing error in sm120 mxfp8 triton path (#19835) 2026-03-29 01:59:24 -07:00
Liangsheng Yin
fec9961a1f Clean up _wait_for_scheduler_ready implementation (#21626) 2026-03-29 01:02:33 -07:00
psaab
d2fa8d67ba Wrap IPv6 addresses in gRPC, bench_serving, and log messages (#21236) 
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-03-29 00:36:31 -07:00