EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
4,977 Commits 8 Branches 0 Tags
646076b71e8d12816d94de44a63ea57a568651de
Commit Graph

146 Commits

Author SHA1 Message Date
Kaixi Hou
5c34b4f1c7 [NVIDIA] [2/N] Optimize silu_and_mul_scaled_fp4_grouped_quant perf (#9556) 2025-08-29 17:17:03 -07:00
hlu1
a7d825fccc Skip some tests on Blackwell (#9777) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-08-28 20:00:32 -07:00
Qi Yuhang
fda4792620 Update CUTLASS 4.2 & Enable K-Major Scale Factor for SM90 FP8 Blockwise Group GEMM (#9559) 2025-08-24 23:24:43 -07:00
Kaixi Hou
e5638573c1 [NVIDA] [1/N] Nvfp4 Masked Gemm: Add quant op for the flashinfer grouped gemm (#9200) 2025-08-22 12:19:45 -07:00
fzyzcjy
e85cb1ce9d Fix quant kernel test errors and benchmark wrong output speeds (#7604) 2025-08-21 03:48:41 -07:00
Trevor Morris
a91e90d9a3 [2/2] Fuse routed scaling factor into select_experts (#8690) 2025-08-20 15:10:16 -07:00
Yichen Yan
c9bf3877a0 Reduce overhead for fa by not calling heavy CUDA property check (#7375) 2025-08-20 16:26:28 +08:00
Yuan Luo
53dcc750b6 [sgl-kernel] Support FlashInfer top_k_top_p_sampling_from_logits (#9060) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-08-14 10:56:36 -07:00
Peng Zhang
5aa1ebd242 [2/n]decouple quantization implementation from vLLM dependency (#8112) 
Co-authored-by: walker-ai <yiyun.wyt@antgroup.com>
Co-authored-by: leoneo <1320612015@qq.com>
 2025-08-14 03:19:03 -07:00
Ke Bao
94f44b88d1 Update fa3 interface and add unit test (#9150) 2025-08-13 20:05:02 +08:00
fzyzcjy
9aea255522 Fuse writing KV buffer into rope kernel (part 1: sgl-kernel) (#9077) 2025-08-12 01:46:40 -07:00
Yineng Zhang
dd949ace23 Revert "[1/2][resubmit] sgl-kernel: Fuse routed scaling factor into m… (#9035) 2025-08-10 17:34:54 -07:00
Trevor Morris
591c232f7c [1/2][resubmit] sgl-kernel: Fuse routed scaling factor into moe_fused_gate (select_experts) (#8770) 2025-08-08 17:55:06 -07:00
Hongbo Xu
39fd178831 refactor: Move scalar_types.py to sgl-kernel to avoid circular import (#8720) 2025-08-07 19:22:16 -07:00
Liangsheng Yin
f9f0138f80 Revert "[1/2] sgl-kernel: Fuse routed scaling factor into select_experts" (#8706) 2025-08-02 20:14:30 +08:00
Trevor Morris
f642524fd9 [1/2] sgl-kernel: Fuse routed scaling factor into select_experts (#8364) 2025-08-01 18:14:24 -07:00
Stefan He
db7343c992 fix per token cuda kernel hidden dim cannot divide by 16 (#8543) 2025-08-01 09:27:18 -07:00
Peter Pan
6bdd27861b [Kimi K2] dsv3_router_gemm supports NUM_EXPERTS == 384 (#8013) 2025-08-01 22:01:24 +08:00
Cheng Wan
a5f5ab4030 update sgl-kernel for EP: kernel part (#8514) 
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
 2025-07-30 22:19:55 -07:00
Ke Bao
5973675bc3 Fix moe align kernel test (#8531) 2025-07-29 11:03:02 -07:00
Ke Bao
8af145b7dc Fix test_moe_fused_gate_combined sgl-kernel ci test (#8374) 2025-07-26 09:30:12 +08:00
Zhiqiang Xie
d40846d456 breakdown kernel update (#8334) 2025-07-25 08:33:17 +08:00
Zhiqiang Xie
b43263307f Hicache IO kernel refactoring (#8264) 2025-07-23 16:49:03 +08:00
Ke Bao
e885bfdc6a Fix sgl-kernel ci test (#8284) 2025-07-23 14:01:47 +08:00
Baizhou Zhang
282eb59ff3 Add bf16 output option for dsv3_router_gemm kernel (#7999) 2025-07-20 09:49:37 +08:00
Peng Zhang
c28ad1990d [1/n] chore: decouple quantization implementation from vLLM dependency (#7992) 2025-07-16 15:56:26 -07:00
Qi Yuhang
c268c11c71 [feat]Support fusion kernel for constructing quant input and scale factor for fp8_blockwise_scaled_grouped_mm (#8023) 2025-07-15 00:02:44 -07:00
ykcombat
1ebec1a8b0 [Feature] CUDA Green Context Support (#7649) 2025-07-15 02:49:16 +08:00
Qi Yuhang
26118a133d [fix]Update unitest for fp8_blockwise_scaled_grouped_mm kernel (#7932) 2025-07-11 14:29:13 -07:00
SijiaYang
da3890e82a [1/n]: add cutlass W4A8 moe kernel for hopper architecture (#7772) 
Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com>
Co-authored-by: yicwang <yichen.wang@bytedance.com>
 2025-07-04 20:50:12 -07:00
Yi Zhang
2998c4bdf4 [optimize] fuse renormalize into moe_topk_softmax (#7744) 
Co-authored-by: ispobock <ispobaoke@gmail.com>
 2025-07-03 12:42:44 -07:00
ayrnb
2c4feaf308 Add CUTLASS FP8 Blockscale MoE kernel for Hopper architecture (#7278) 
Co-authored-by: HydraQYH <QYH820@Outlook.com>
Co-authored-by: TianQiLin666666 <1834987979@qq.com>
 2025-07-02 23:27:03 -07:00
AniZpZ
8e03b641ba [1/n] apply wna16marlin kernel in moe weight only quantization (#7683) 
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: yych0745 <1398089567@qq.com>
Co-authored-by: HandH1998 <1335248067@qq.com>
Co-authored-by: 弋云 <yiyun.wyt@antgroup.com>
Co-authored-by: walker-ai <2398833647@qq.com>
 2025-07-01 23:21:25 -07:00
Baizhou Zhang
7248272ccc Add dsv3 router gemm kernel (#7627) 2025-06-29 23:31:55 -07:00
Ke Bao
04b35190e2 Add dsv3 fused a gemm to sgl-kernel (#7630) 2025-06-29 02:52:24 -07:00
Ke Bao
57ab776910 Fuse sorted_token_ids padding to moe_align_block_size kernel (#7437) 2025-06-24 17:44:27 -07:00
Zhiqiang Xie
34c3f9b2d3 kvcache io kernels and test case (#7382) 2025-06-23 11:58:59 -07:00
xutizhou
506c4928f5 feat: integrate deepgemm into EPMoE (#6821) 
Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com>
Co-authored-by: TianQiLin666666 <1834987979@qq.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
 2025-06-23 01:38:58 -07:00
Yineng Zhang
0650e5176f fix: only enable flash_attn test on sm80 sm90 (#7289) 2025-06-17 16:56:41 -07:00
AniZpZ
3eb4a800e8 Fix AWQ Dequant and Weight Loading of deepseek v2 (#6842) 2025-06-17 13:45:10 -07:00
Lianmin Zheng
cfceb83d05 Fix sampling for speculative decoding & simplify kernels (#7207) 2025-06-16 03:28:30 -07:00
JieXin Liang
ab1a4fa5cb [fix] fix cutlass_mla_backend with cuda_graph and add sm_scale for sgl-kernel cutlass_mla (#7184) 2025-06-14 12:45:41 -07:00
fzyzcjy
5c66c4424f Support new DeepGEMM format in per token group quant (#7146) 2025-06-13 02:00:22 -07:00
fzyzcjy
aa46ed34d2 Remove 200us slow concat kernel (part 1: kernel) (#7145) 2025-06-13 01:58:29 -07:00
Yuan Luo
84727a5139 [sgl-kernel] Add cuda kernel for moe_ep_silu_and_mul (#6919) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-06-11 20:43:08 -07:00
JieXin Liang
18efb5e8e0 [perf][sgl-kernel] extend cutlass_mla_decode to support num_head < 128 (#6929) 2025-06-08 19:37:34 -07:00
Yuan Luo
43baba649e [EP] Add cuda kernel for moe_ep_post_reorder (#6837) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-06-05 00:33:47 -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
Xiaoyu Zhang
bd75690f4e fix ep_moe_reorder kernel bugs (#6858) 
Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com>
 2025-06-04 19:13:59 +08:00