Commits · 59aab76f0a8ccdb8babd9fd278d09a13e665bdc2 · change / sglang · GitLab

29 Jul, 2025 1 commit
- Fix moe align kernel test (#8531) · 5973675b
  Ke Bao authored Jul 30, 2025
  
  5973675b
26 Jul, 2025 1 commit
- Fix test_moe_fused_gate_combined sgl-kernel ci test (#8374) · 8af145b7
  Ke Bao authored Jul 26, 2025
  
  8af145b7
25 Jul, 2025 1 commit
- breakdown kernel update (#8334) · d40846d4
  Zhiqiang Xie authored Jul 24, 2025
  
  d40846d4
23 Jul, 2025 2 commits
- Hicache IO kernel refactoring (#8264) · b4326330
  Zhiqiang Xie authored Jul 23, 2025
  
  b4326330
- Fix sgl-kernel ci test (#8284) · e885bfdc
  Ke Bao authored Jul 23, 2025
  
  e885bfdc
20 Jul, 2025 1 commit
- Add bf16 output option for dsv3_router_gemm kernel (#7999) · 282eb59f
  Baizhou Zhang authored Jul 19, 2025
  
  282eb59f
16 Jul, 2025 1 commit
- [1/n] chore: decouple quantization implementation from vLLM dependency (#7992) · c28ad199
  Peng Zhang authored Jul 17, 2025
  
  c28ad199
15 Jul, 2025 1 commit
- [feat]Support fusion kernel for constructing quant input and scale factor for... · c268c11c
  Qi Yuhang authored Jul 15, 2025
```
[feat]Support fusion kernel for constructing quant input and scale factor for fp8_blockwise_scaled_grouped_mm (#8023)
```
  c268c11c
14 Jul, 2025 1 commit
- [Feature] CUDA Green Context Support (#7649) · 1ebec1a8
  ykcombat authored Jul 15, 2025
  
  1ebec1a8
11 Jul, 2025 1 commit
- [fix]Update unitest for fp8_blockwise_scaled_grouped_mm kernel (#7932) · 26118a13
  Qi Yuhang authored Jul 12, 2025
  
  26118a13
05 Jul, 2025 1 commit

[1/n]: add cutlass W4A8 moe kernel for hopper architecture (#7772) · da3890e8

SijiaYang authored Jul 05, 2025


Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com>
Co-authored-by: yicwang <yichen.wang@bytedance.com>

da3890e8

03 Jul, 2025 2 commits
- [optimize] fuse renormalize into moe_topk_softmax (#7744) · 2998c4bd
  Yi Zhang authored Jul 04, 2025
```
Co-authored-by: ispobock <ispobaoke@gmail.com>
```
  2998c4bd
- Add CUTLASS FP8 Blockscale MoE kernel for Hopper architecture (#7278) · 2c4feaf3
  ayrnb authored Jul 03, 2025
```
Co-authored-by: HydraQYH <QYH820@Outlook.com>
Co-authored-by: TianQiLin666666 <1834987979@qq.com>
```
  2c4feaf3
02 Jul, 2025 1 commit

[1/n] apply wna16marlin kernel in moe weight only quantization (#7683) · 8e03b641

AniZpZ authored Jul 02, 2025


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>

8e03b641

30 Jun, 2025 1 commit
- Add dsv3 router gemm kernel (#7627) · 7248272c
  Baizhou Zhang authored Jun 29, 2025
  
  7248272c
29 Jun, 2025 1 commit
- Add dsv3 fused a gemm to sgl-kernel (#7630) · 04b35190
  Ke Bao authored Jun 29, 2025
  
  04b35190
25 Jun, 2025 1 commit
- Fuse sorted_token_ids padding to moe_align_block_size kernel (#7437) · 57ab7769
  Ke Bao authored Jun 25, 2025
  
  57ab7769
23 Jun, 2025 2 commits

kvcache io kernels and test case (#7382) · 34c3f9b2
Zhiqiang Xie authored Jun 23, 2025

34c3f9b2

feat: integrate deepgemm into EPMoE (#6821) · 506c4928

xutizhou authored Jun 23, 2025


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>

506c4928

17 Jun, 2025 2 commits
- fix: only enable flash_attn test on sm80 sm90 (#7289) · 0650e517
  Yineng Zhang authored Jun 17, 2025
  
  0650e517
- Fix AWQ Dequant and Weight Loading of deepseek v2 (#6842) · 3eb4a800
  AniZpZ authored Jun 18, 2025
  
  3eb4a800
16 Jun, 2025 1 commit
- Fix sampling for speculative decoding & simplify kernels (#7207) · cfceb83d
  Lianmin Zheng authored Jun 16, 2025
  
  cfceb83d
14 Jun, 2025 1 commit
- [fix] fix cutlass_mla_backend with cuda_graph and add sm_scale for sgl-kernel cutlass_mla (#7184) · ab1a4fa5
  JieXin Liang authored Jun 15, 2025
  
  ab1a4fa5
13 Jun, 2025 2 commits
- Support new DeepGEMM format in per token group quant (#7146) · 5c66c442
  fzyzcjy authored Jun 13, 2025
  
  5c66c442
- Remove 200us slow concat kernel (part 1: kernel) (#7145) · aa46ed34
  fzyzcjy authored Jun 13, 2025
  
  aa46ed34
12 Jun, 2025 1 commit
- [sgl-kernel] Add cuda kernel for moe_ep_silu_and_mul (#6919) · 84727a51
  Yuan Luo authored Jun 12, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  84727a51
09 Jun, 2025 1 commit
- [perf][sgl-kernel] extend cutlass_mla_decode to support num_head < 128 (#6929) · 18efb5e8
  JieXin Liang authored Jun 09, 2025
  
  18efb5e8
05 Jun, 2025 2 commits
- [EP] Add cuda kernel for moe_ep_post_reorder (#6837) · 43baba64
  Yuan Luo authored Jun 05, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  43baba64
- support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277) · 8e3797be
  zyksir authored Jun 05, 2025
  
  8e3797be
04 Jun, 2025 3 commits
- Set `num_fused_shared_experts` as `num_shared_experts` when shared_experts... · 81964328
  Cheng Wan authored Jun 04, 2025
```
Set `num_fused_shared_experts` as `num_shared_experts` when shared_experts fusion is not disabled (#6736)
```
  81964328
- fix ep_moe_reorder kernel bugs (#6858) · bd75690f
  Xiaoyu Zhang authored Jun 04, 2025
```
Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com>
```
  bd75690f
- [Refactor] Rename `n_share_experts_fusion` as `num_fused_shared_experts` (#6735) · 8a548052
  Cheng Wan authored Jun 03, 2025
  
  8a548052
26 May, 2025 1 commit
- [FA][Test] Fix Sparse FA test (#6306) · 006ead9d
  Brayden Zhong authored May 26, 2025
  
  006ead9d
22 May, 2025 2 commits
- Add main for merge state tests (#6492) · 121f92c5
  Yuan Luo authored May 22, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  121f92c5
- [1/2] Support Qserve (#6457) · 4d643f6c
  HandH1998 authored May 22, 2025
```
Co-authored-by: yych0745 <1398089567@qq.com>
Co-authored-by: sleepcoo <sleepcoo@gmail.com>
```
  4d643f6c
16 May, 2025 1 commit
- [2/2] Add python wrapper for CUTLASS FP8 Blockscale MoE Kernel. (#5694) · 6fc93575
  Elfie Guo authored May 16, 2025
  
  6fc93575
12 May, 2025 2 commits
- Revert "fix some typos" (#6244) · e8e18dcd
  Lianmin Zheng authored May 12, 2025
  
  e8e18dcd
- fix some typos (#6209) · d738ab52
  applesaucethebun authored May 12, 2025
```
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  d738ab52
11 May, 2025 1 commit
- Add typo checker in pre-commit (#6179) · 2ce87935
  applesaucethebun authored May 11, 2025
```
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  2ce87935
09 May, 2025 1 commit
- Cutlass MLA: Disable split kv due to https://github.com/NVIDIA/cutlass/issues/2274 (#6101) · 0ab3f437
  Trevor Morris authored May 08, 2025
  
  0ab3f437