COMMITS
July 29, 2025
L
Fix indent
LJC00118 committed
D
Merge pull request #135 from danthe3rd/patch-3
dan_the_3rd committed
July 28, 2025
Y
Add torch as build dependency. (#139)
Yuxian Qiu committed
D
Update system.hpp (#133)
dan_the_3rd committed
D
Update setup.py (#134)
dan_the_3rd committed
July 21, 2025
R
C
Updated submodules to use https:// vs git@ (#129)
Clayton Coleman committed
July 20, 2025
Y
fix: update .gitmodules (#130)
Yineng Zhang committed
July 18, 2025
R
Update CUDA toolkits requirement (#128)
Ray Wang committed
R
Add more GPU architectures support (#112)
Ray Wang committed
July 2, 2025
C
Simplify expression
Chenggang Zhao committed
F
[add] fix smem_barrier size in wgrad way (#122)
fy1214 committed
June 23, 2025
June 16, 2025
S
Fix illegal memory address when skipping -1 m indices (#113)
shixianc committed
May 27, 2025
Y
Grouped GEMM skip useless computation for unaligned Ms (#103)
yukuai26 committed
May 16, 2025
C
Fix JIT tests
Chenggang Zhao committed
May 15, 2025
C
Add a missing `#pragma once`
Chenggang Zhao committed
C
Merge pull request #100 from deepseek-ai/remove-tuner
Chenggang Zhao committed
C
Add `__assertfail`
Chenggang Zhao committed
C
Unify `kwargs` usages
Chenggang Zhao committed
C
Unify `ceil_div`s
Chenggang Zhao committed
C
Add `DG_PRINT_CONFIGS`
Chenggang Zhao committed
C
Refactor launch-related structures
Chenggang Zhao committed
May 14, 2025
C
Cleanup some useless staffs
Chenggang Zhao committed
C
Update plans
Chenggang Zhao committed
Z
Weight gradient kernels for dense and MoE models (#95)
Zhean Xu committed
May 7, 2025
C
Update README with NVRTC news
Chenggang Zhao committed
C
Fix 12.9 compatibility
Chenggang Zhao committed