Commits · 3fa62da78c120be7103bfcb6fd1405d3630d6c98 · change / sglang

06 Sep, 2025 1 commit
- [7/N] MoE Refactor: the implementation of new framework (#9269) · 3fa62da7
  Cheng Wan authored Sep 05, 2025
  
  3fa62da7
05 Sep, 2025 1 commit
- Forbid DeepEP racing condition when too many tokens (#9567) · adf73175
  fzyzcjy authored Sep 05, 2025
  
  adf73175
15 Aug, 2025 1 commit
- [6/N] MoE Refactor: Cleanup MoE-related configs (#8849) · 29589512
  Cheng Wan authored Aug 14, 2025
  
  29589512
09 Aug, 2025 1 commit
- [Feature] Optimize DeepSeek's DeepEP on Ascend NPU (#8355) · 137e75da
  Even Zhou authored Aug 09, 2025
```
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: Hexq0210 <hexq0809521@gmail.com>
```
  137e75da
01 Aug, 2025 1 commit
- [5/N] MoE Refactor: Update MoE parallelism arguments (#8658) · 6c88f6c8
  Cheng Wan authored Aug 01, 2025
  
  6c88f6c8
29 Jul, 2025 1 commit
- Tiny add warnings for DeepEP when it is suboptimal (#8426) · 59d0bf01
  fzyzcjy authored Jul 29, 2025
  
  59d0bf01
28 Jul, 2025 1 commit
- [3/N] MoE Refactor: Simplify DeepEP Output (#8421) · 9c138a04
  Cheng Wan authored Jul 28, 2025
  
  9c138a04
05 Jul, 2025 1 commit
- DP Attention with Auto DeepEP Dispatch (#7222) · 8fc910db
  Cheng Wan authored Jul 05, 2025
  
  8fc910db
29 Jun, 2025 1 commit
- Move files related to EPLB (#7580) · 0c9c6c75
  fzyzcjy authored Jun 30, 2025
  
  0c9c6c75
28 Jun, 2025 1 commit
- Let EP prefill support new DeepGEMM (#7310) · 00c7b1ad
  fzyzcjy authored Jun 28, 2025
  
  00c7b1ad
24 Jun, 2025 1 commit
- [AMD] add aiter fused moe in DeepEP path (#7268) · 755f3147
  Alex Sun authored Jun 24, 2025
  
  755f3147
16 Jun, 2025 2 commits
- [fix] fix DeepGEMM blackwell input quant & ut & fix style and log (#7247) · 5ca07eed
  JieXin Liang authored Jun 17, 2025
  
  5ca07eed
- Tiny remove comments about DeepEP on H20 (#7234) · 91a066ec
  fzyzcjy authored Jun 17, 2025
  
  91a066ec
15 Jun, 2025 1 commit
- Fix error when disabling new DeepGEMM (#7198) · 349bb2c9
  fzyzcjy authored Jun 15, 2025
  
  349bb2c9
14 Jun, 2025 2 commits
- Support new DeepGEMM (#7172) · 93cec433
  fzyzcjy authored Jun 14, 2025
  
  93cec433
- Refactor DeepGEMM integration (#7150) · b4c41f72
  fzyzcjy authored Jun 14, 2025
  
  b4c41f72
13 Jun, 2025 1 commit
- Fix DeepEP error in some environments (#7154) · b04df75a
  fzyzcjy authored Jun 14, 2025
  
  b04df75a
07 Jun, 2025 1 commit
- Tiny support customize DeepEP max dispatch tokens per rank (#6934) · 61ce91ed
  fzyzcjy authored Jun 07, 2025
  
  61ce91ed
27 May, 2025 1 commit
- Fix DeepEP error in Qwen 3 MoE models (#6673) · a564e001
  fzyzcjy authored May 28, 2025
  
  a564e001
21 May, 2025 2 commits
- Tiny add stage assertions to DeepEPDispatcher to avoid misuse (#6467) · a071dc40
  fzyzcjy authored May 21, 2025
  
  a071dc40
- Fix num_qps_per_rank computation when providing custom DeepEP configuration (#6468) · a40aecc5
  fzyzcjy authored May 21, 2025
  
  a40aecc5
20 May, 2025 1 commit
- Expert distribution recording without overhead for EPLB (#4957) · f0653886
  fzyzcjy authored May 20, 2025
  
  f0653886
18 May, 2025 1 commit
- Support custom DeepEP tuning config (#6257) · fd08c048
  fzyzcjy authored May 18, 2025
  
  fd08c048
08 May, 2025 1 commit

DeepEP normal support deepgemm-contiguous (#5626) · acc816d8

lukec authored May 08, 2025


Co-authored-by: Yingyi Huang <yingyihuang2000@outlook.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Xuting Zhou <xutingz@nvidia.com>
Co-authored-by: ZhengHSI <zhenghsi@qq.com>

acc816d8

30 Apr, 2025 1 commit

[PD] Fix Assertion failed: /DeepEP/csrc/kernels/internode.cu:483, condition:... · cc4a80ca

ybyang authored Apr 30, 2025

[PD] Fix Assertion failed: /DeepEP/csrc/kernels/internode.cu:483, condition: ibgda_get_state()->num_rc_per_pe >= num_channels #134 (#5830)

cc4a80ca

09 Apr, 2025 2 commits
- [DeepEP] fix: import buffer error (#5179) · 76c48a09
  Cheng Wan authored Apr 09, 2025
  
  76c48a09
- [Fix] DeepEP Compatibility with Low Latency (#5068) · bc3f6db2
  Jinyan Chen authored Apr 09, 2025
```
Co-authored-by: ch-wan <cwan39@gatech.edu>
```
  bc3f6db2
04 Apr, 2025 3 commits
- Cleanup unused resources after DeepEP operation (#4996) · 6ff9c6a5
  fzyzcjy authored Apr 04, 2025
  
  6ff9c6a5
- Support async DeepEP by splitting into two stages (#4995) · 77e929a1
  fzyzcjy authored Apr 04, 2025
  
  77e929a1
- Small refactor DeepEPDispatcher into subclasses (#4994) · febe21ce
  fzyzcjy authored Apr 04, 2025
  
  febe21ce
03 Apr, 2025 1 commit
- Small refactor DeepEPMode to clean up code a bit (#4992) · 8e10fec9
  fzyzcjy authored Apr 03, 2025
  
  8e10fec9
01 Apr, 2025 1 commit

[Feature] Support DeepEP Low Latency (#4767) · 23c764b1

Jinyan Chen authored Apr 02, 2025


Co-authored-by: sleepcoo <sleepcoo@gmail.com>
Co-authored-by: laixinn <xielx@shanghaitech.edu.cn>
Co-authored-by: ch-wan <cwan39@gatech.edu>

23c764b1

23 Mar, 2025 2 commits
- Support async in DeepEP (#4610) · ca75741e
  fzyzcjy authored Mar 23, 2025
```
Co-authored-by: Cheng Wan <cwan39@gatech.edu>
```
  ca75741e
- Multiple tiny code cleanups (#4608) · c6d549e7
  fzyzcjy authored Mar 23, 2025
  
  c6d549e7
22 Mar, 2025 1 commit
- Optimize Permute Kernel in DeepEP (#4643) · c2bd094d
  xutizhou authored Mar 23, 2025
```
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
```
  c2bd094d
19 Mar, 2025 1 commit

[Feature] Integrate DeepEP into SGLang (#4232) · f44db16c

Jinyan Chen authored Mar 19, 2025


Co-authored-by: Cheng Wan <cwan39@gatech.edu>
Co-authored-by: Xuting Zhou <xutingz@nvidia.com>

f44db16c