chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
9,993 Commits 1 Branch 0 Tags
a55f6588350c754cfc7ff0a5a0f8b75a5fde6dfa
Commit Graph

6520 Commits

Author SHA1 Message Date
Julian Huang
a55f658835 [Misc] Normalize --host parameter to use plain hostname without scheme (#19309) 
Co-authored-by: 墨楼 <huangzhilin.hzl@antgroup.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-02-25 00:37:24 -08:00
YAMY
f75abb4521 [Fix][Qwen3.5] Fix KV cache slice transfer for GQA models with replicated KV heads (#19086) 
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-02-25 16:26:44 +08:00
huangtingwei
d40cb2f725 [HiCache] Support heterogeneous tp for hicache storage (#18541) 
Co-authored-by: hzh0425 <hzh0425@apache.org>
 2026-02-25 00:13:57 -08:00
Wang, Yi
3d879c69e9 refactor: extract device-to-backend mapping into get_default_distributed_backend (#19202) 
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-02-24 23:50:26 -08:00
Hexq0210
d0bb140034 [NPU] bugfix for model Qwen3-Coder-Next at weight shape transpose for npu. (#18700) 
Co-authored-by: McZyWu <zhuoyun.wu.23@ucl.ac.uk>
 2026-02-25 15:46:20 +08:00
xutizhou
a1b39c1c26 Perf/fuse mamba state scatter mtp verify (#18088) 2026-02-25 15:40:55 +08:00
lw9527
4a3a787f1e [Fix] Kimi K2.5 support pp (#18434) 
Co-authored-by: Ilya Boytsov <ilya.boytsov@aleph-alpha.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-02-25 15:22:11 +08:00
Shangming Cai
8d9ee6669e Fix comment for tp_rank calculation in dp_attention (#19306) 2026-02-25 15:19:10 +08:00
Hubert Lu
17b0affbdf [AMD] Support --enable-aiter-allreduce-fusion on AMD GPUs (#13747) 
Co-authored-by: yctseng0211 <yctseng@amd.com>
 2026-02-24 23:11:55 -08:00
YAMY
73fe389dd1 [Qwen3.5] Raise Exception when radix_cache and extra_buffer are enabled at the same time (#19169) 2026-02-25 15:04:37 +08:00
Liangsheng Yin
76d5410e01 [Disagg] Fix decode querying unregistered dp_rank when prefill dp_size is 1 (#19305) 
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
 2026-02-24 22:52:39 -08:00
Hubert Lu
8bd644765f [AMD] Enable ROCm kvcache JIT path and add AMD CI coverage. (#18992) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-25 14:15:05 +08:00
Michael
ca09d71cf0 Fix nightly grok failure on rotary embedding import (#19192) 
Co-authored-by: michaelzhang-ai <michaelzhang-ai@users.noreply.github.com>
 2026-02-25 13:25:16 +08:00
jacky.cheng
e138f7960a [AMD] Fix accuracy while using --enable-dp-attention (#19247) 
Co-authored-by: yichiche@amd.com <jacky.cheng>
 2026-02-24 20:50:28 -08:00
Liangsheng Yin
ab0f608788 [PD-Disagg] Fix bootstrap server race condition when prefill workers not yet registered (#19288) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-24 20:22:16 -08:00
Liangsheng Yin
539f772f54 [PD-Disagg] Fully support external DP dispatch w/ PD-disaggregation mode. (#19268) 
Co-authored-by: Ratish P <114130421+ratish1@users.noreply.github.com>
 2026-02-24 19:58:01 -08:00
Mick
241ee90164 [diffusion] chore: tiny fix pyproject.toml (#19256) 2026-02-25 11:57:53 +08:00
Shangming Cai
0fac2796b6 [PD-Disagg] Improve KVManager init across all backends (#19240) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2026-02-25 10:37:09 +08:00
siyu
c0fdfd4b92 Delete mm.feature after decode phase (#17324) 2026-02-24 18:13:03 -08:00
Xiaoyu Zhang
9dff933164 [Kernel Slimming] Remove sgl-kernel AOT marlin kernels (#19241) 2026-02-25 10:08:22 +08:00
Feng Su
3b89302277 Refactor: observability code cleanup (#17862) 
Signed-off-by: Feng Su <sufeng@linux.alibaba.com>
 2026-02-24 18:07:29 -08:00
siyu
245430eaac Encoder Global Cache Manager (#16137) 
Co-authored-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>
 2026-02-24 18:05:43 -08:00
fzyzcjy
b7af58b9af Support replication axis in dump comparator (#19282) 2026-02-25 09:48:43 +08:00
fzyzcjy
2e2b18e870 Support context parallel zigzag reordering in dump comparator (#19281) 2026-02-25 09:46:17 +08:00
fzyzcjy
0de1f4b07b Support multi axis unsharding in dump comparator (#19280) 2026-02-25 09:44:07 +08:00
fzyzcjy
4bb678f28a Full test coverage in dump comparator (#19279) 2026-02-25 09:43:29 +08:00
fzyzcjy
94ca2ac5d7 Support TP unification and enhance tests in dump comparator (#19278) 2026-02-25 09:42:56 +08:00
fzyzcjy
39ba9b5ab5 Support simple unsharding in dumper comparator (#19277) 2026-02-25 09:42:21 +08:00
fzyzcjy
02ca107b2c Support dims annotation and enhance dump loader in dumper (#19276) 2026-02-25 09:41:48 +08:00
fzyzcjy
8b1ab4aaf9 Support agent-friendly output formats in dump comparator (#19275) 2026-02-25 09:40:33 +08:00
fzyzcjy
d7578ce279 Implement simplest dump comparator v2 (#19274) 2026-02-25 09:37:21 +08:00
wxy
9cec98b445 [diffusion] fix: shard timestep_proj in sequence-sharded ti2v (#19237) 2026-02-25 09:33:45 +08:00
Mick
0ede5c54a8 [diffusion] logging: improve request and component load logs (#19253) 2026-02-25 09:32:36 +08:00
silencejade
15f2e36fb9 [NPU] forward_npu uses native impl by default in MultiPlatformOp (#18545) 2026-02-25 09:16:09 +08:00
Chen, Zhentao
b9cf1563de [ROCm] Optimize Deepseek R1 on MI300X (#18242) 
Co-authored-by: Chen, Todd <zhenchen@amd.com>
 2026-02-24 17:01:14 -08:00
Vladimir221
f1088beb6a [NPU]Optimization of forward_npu for UnquantizedFusedMoEMethod (#13158) 2026-02-25 08:55:20 +08:00
Jonah Bernard
d7a03c7ebf [MoE Refactor] Refactor FlashInferFusedMoE into FusedMoE and flashinfer_trtllm.py (#19266) 2026-02-24 16:47:53 -08:00
Chen, Zhentao
c193a52fa2 [AMD] DSR1/V3 use fp8 bmm in MLA for MI300X (#18624) 
Co-authored-by: Chen, Todd <zhenchen@amd.com>
 2026-02-24 15:33:33 -08:00
Ratish P
ae6f6e1495 [Refactor] Benchmark: Add typed DatasetArgs/Loader registry and CPU dataset unit tests (#19147) 
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2026-02-24 12:22:01 -08:00
Glen Liu
a06425184f [Fix] remove redundant +1 when getting tail_str for Req (#18584) 2026-02-24 10:35:26 -08:00
Makcum888e
9bce3b040c [diffusion] [NPU] Update perf baselines (#19227) 2026-02-24 21:15:16 +03:00
Zihao Wang
e6ad58e5da [diffusion] fix: webui not return data (#19244) 2026-02-24 23:39:06 +08:00
Adarsh Shirawalmath
1efc33c640 [diffusion] refactor: remove enums and unify attention backends (#19149) 2026-02-24 21:21:23 +08:00
triple-mu
ea1bc1c578 [diffusion] feat: optimize all_to_all (#19157) 2026-02-24 21:20:10 +08:00
Yuan Luo
31c7dc9d99 [VLM] Introduce FlashInfer CUDNN Prefill as ViT Backend (#19003) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-02-24 19:49:22 +08:00
xdtbynd
1a83b2c15d fix: fix the bug blocking completion template application (#17010) 
Co-authored-by: xdtbynd <supercluster@vip.qq.com>
Co-authored-by: cy <chenyang08056032@163.com>
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
 2026-02-24 18:50:08 +08:00
Cheng Wan
6e54361608 Refactor CUDA graph input buffers with shared buffer pool (#19180) 2026-02-24 02:24:40 -08:00
jianzhao-xu
94946764a4 bugfix: The default value of the environment virable is None, so that… (#18309) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
 2026-02-24 18:10:21 +08:00
GMI Xiao Jin
fcfd964d7d [diffusion] model: LTX-2 Support PR3 (#19151) 2026-02-24 16:55:28 +08:00
Simo Lin
88a7e48108 fix(grpc): handle embedding requests in _handle_batch_output (#19221) 
Signed-off-by: Simo Lin <linsimo.mark@gmail.com>
 2026-02-23 22:32:16 -08:00