chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity
6,820 Commits 1 Branch 0 Tags
7b79cc4fe2b247c8697c4e0475c5ac4e775affb4
Commit Graph

118 Commits

Author SHA1 Message Date
Junlin Zhou
0779c3d148 docs: update fused MoE config path (#13211) 2025-11-13 11:14:01 -08:00
Shu Wang
6664083522 Replace [silu_and_mul_]scaled_fp4_group_quant by Flashinfer equivalent (#12376) 2025-11-13 00:26:00 -08:00
Hubert Lu
e4b2937017 [AMD] Add AITER Custom All-Reduce (#13102) 
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: HaiShaw <hixiao@gmail.com>
 2025-11-12 21:53:44 -08:00
Xiaoyu Zhang
f18ec927f3 fix tuning_fused_moe_triton_sep tool per_channel_quant bug (#13027) 2025-11-11 10:33:54 +08:00
Xiaoyu Zhang
fc84b0730c [Refactor] Refactor fused_moe_triton tuning tools: extract shared utils, add EP/MLLM support, reduce overhead (#12440) 
Co-authored-by: xu-yfei <xu-yfei@users.noreply.github.com>
Co-authored-by: Yongfei Xu <xuyongfei.xyf@antgroup.com>
 2025-11-06 20:54:42 +08:00
Yuan Luo
819fc59123 Add prefix for torch symm mem (#12506) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-11-02 11:23:05 -08:00
Xinyuan Tong
82cfcd3bb8 [Refactor] tuning_fused_moe for MLLM and small refactor (#11224) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-10-31 08:54:14 +08:00
Chen1022
1ed1abfd45 feat: add EP support in tuning (#12012) 2025-10-30 07:58:50 -07:00
Xiaoyu Zhang
04e5b6faa7 Revert "Triton fused_moe_kernel support ep moe tuning" (#12377) 2025-10-30 07:12:06 -07:00
Xiaoyu Zhang
52694b60da Triton fused_moe_kernel support ep moe tuning (#12343) 2025-10-29 23:16:09 +08:00
Liana Koleva
1357397a34 feat: preview filename from tuning_fused_moe_triton.py (#12276) 
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2025-10-29 16:12:25 +08:00
Yongfei Xu
d2b8c4123e Opt fused triton moe: add tma for down proj kernel (#10567) 
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
 2025-10-28 14:26:17 +08:00
Zhengyi Lai
81fd2b0ee0 fix(deepep): resolve benchmark failure on 4×IB-card setup by aligning tuning config with DeepEP commit bdd119f8 (#11965) 2025-10-22 21:20:54 -07:00
Liangsheng Yin
9d61205dac [lint] improve ruff check (#11922) 
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2025-10-22 11:32:50 +08:00
Cheng Wan
5b214b50b6 [Refactor] move deep_gemm_wrapper out of quantization (#11784) 2025-10-17 18:57:54 -07:00
Cheng Wan
3c06b673af [8/N] MoE Refactor: deprecate EPMoE (#11211) 2025-10-07 21:51:41 -07:00
Yuan Luo
4f42c8cd3e [sgl-kernel] Support float64 moe_sum_reduce cuda kernel (#11068) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-10-07 14:31:11 +00:00
Yuan Luo
590f2da052 [Feat] Support Torch Symm Mem AllReduce (#10571) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-10-05 13:55:19 -07:00
Yuan Luo
42245551ef [sgl-kernel] Optimize concat_mla_k kernel (#10543) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: PGFLMG <1106310035@qq.com>
 2025-09-28 23:04:22 +08:00
lukec
77830a265e Add fuse_moe per-channel tune (#10915) 2025-09-25 21:12:09 +08:00
Xiaoyu Zhang
c4e314f986 Restruct sgl-kernel benchmark (#10861) 2025-09-25 07:45:25 +08:00
Yiakwy
984730b732 add tunning files for QWEN-3-NEXT (#10794) 2025-09-23 12:46:30 -07:00
Yuan Luo
616a3e20df [sgl-kernel] Support moe_sum_reduce cuda kernel (#10321) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2025-09-19 14:12:09 +08:00
strgrb
fac07c9b08 Support LingV2 model (#10359) 
Co-authored-by: 羽癫 <yudian.zy@antgroup.com>
Co-authored-by: guoyuhong <yuhong.gyh@antgroup.com>
 2025-09-11 23:53:52 -07:00
Yuan Luo
cb3918a091 Optimize moe_sum_reduce_kernel (#9477) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2025-09-07 09:16:18 +08:00
Xiaoyu Zhang
b1fb7e458c [benchmark] add flashinfer_allreduce_fusion benchmark (#9937) 2025-09-03 16:31:01 +08:00
Kaixi Hou
5c34b4f1c7 [NVIDIA] [2/N] Optimize silu_and_mul_scaled_fp4_grouped_quant perf (#9556) 2025-08-29 17:17:03 -07:00
ehuaa
8f7b1c31e8 Add A100 fused MoE kernel configs for Dpsk (#9677) 2025-08-26 20:49:48 -07:00
Yineng Zhang
f8b757bcac fix: resolve tuning fused moe issue (#9587) 2025-08-25 01:41:15 -07:00
Even Zhou
de2dd73831 Revert "[feature] Rework Ascend NPU graph support" (#9385) 2025-08-20 00:35:10 -07:00
Even Zhou
3680d6f88b [feature] Rework Ascend NPU graph support (#9350) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: yezhifeng (D) <y00897525@china.huawei.com>
Co-authored-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: Maksim <makcum888e@mail.ru>
Co-authored-by: ssshinigami <44640852+ssshinigami@users.noreply.github.com>
 2025-08-19 20:32:27 -07:00
Chang Su
46fe8b8cb2 [CI] Fix lint issues (#9361) 2025-08-19 13:05:36 -07:00
mpashkovskiy
a3b810ebdb fix: enable multi-GPU Triton fused MoE tuning (#6295) 2025-08-19 10:16:58 -07:00
Even Zhou
f4fafacc5d Revert "[feature] Ascend NPU graph support (#8027)" (#9348) 2025-08-19 10:11:23 -07:00
Yuan Luo
968e181826 Fix triton_fused_moe unit test and benchmark (#9276) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-08-18 00:54:33 -07:00
VDV1985
94371dbbd6 [feature] Ascend NPU graph support (#8027) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: yezhifeng (D) <y00897525@china.huawei.com>
Co-authored-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: Maksim <makcum888e@mail.ru>
Co-authored-by: ssshinigami <44640852+ssshinigami@users.noreply.github.com>
 2025-08-16 17:25:17 -07:00
Cheng Wan
295895120d [6/N] MoE Refactor: Cleanup MoE-related configs (#8849) 2025-08-14 21:14:53 -07:00
Ke Bao
0475448ee3 Optimize triton swa kernel by skipping computation (#8860) 2025-08-06 21:37:50 +08:00
Yineng Zhang
1466c1b896 feat: support glm4 tuning (#8473) 2025-07-28 14:32:58 -07:00
Yuxuan Zhang
6d6a8bc278 GLM-4.5 Model Support (#8224) 
Co-authored-by: Lifu Huang <lifu.hlf@gmail.com>
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
 2025-07-27 22:54:07 -07:00
Cheng Wan
abda2542d5 Fix tuning_fused_moe_triton.py (#8175) 2025-07-19 17:33:50 -07:00
Yuan Luo
253454de9b Integrate triton moe kernel (#7689) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-07-06 20:05:49 -07:00
Xiaoyu Zhang
0ae1e9a755 refine fused_moe benchmark (#7221) 2025-06-15 21:21:32 -07:00
Quanfeng Li
ef32677444 Fix positional argument (#7093) 2025-06-11 18:31:13 -07:00
Xiaoyu Zhang
3712abfaf9 Fuse routed scaling factor in deepseek (#6970) 2025-06-08 15:24:24 -07:00
Xiaoyu Zhang
fa3592cfeb rebase h20 fused_moe config (#6966) 2025-06-08 05:01:34 -07:00
Yineng Zhang
1fb76ebb93 Revert "Fuse routed scaling factor in topk_reduce kernel (#6220)" (#6968) 2025-06-07 21:02:49 -07:00
Xiaoyu Zhang
515ef4facb Fuse routed scaling factor in topk_reduce kernel (#6220) 2025-06-07 11:06:50 -07:00
zyksir
8e3797be1c support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277) 2025-06-04 22:11:24 -07:00
Cheng Wan
81964328b7 Set num_fused_shared_experts as num_shared_experts when shared_experts fusion is not disabled (#6736) 2025-06-04 15:53:22 -07:00