COMMITS
May 7, 2025
C
Add `DG_PRINT_AUTOTUNE` to README
Chenggang Zhao committed
C
Fix pipeline stage edge cases
Chenggang Zhao committed
G
Refactor JIT compilation (+NVRTC support) (#94)
Gabriel Wu committed
April 28, 2025
C
Less stages for small shape K
Chenggang Zhao committed
April 27, 2025
C
Add two more optimization TODOs
Chenggang Zhao committed
April 24, 2025
C
Update plans
Chenggang Zhao committed
April 23, 2025
Y
Indivisible TMA (#90)
yukuai26 committed
April 21, 2025
Y
Support TMA multicast on B with m_grouped_gemm_contiguous. (#88)
yukuai26 committed
April 18, 2025
C
Update README
Chenggang Zhao committed
C
Overlap TMA store
Chenggang Zhao committed
April 14, 2025
Z
Refactor MMA template with CUTLASS (#87)
Zhean Xu committed
C
Use swizzling instead of padding (#86)
Chenggang Zhao committed
April 11, 2025
C
Merge pull request #83 from deepseek-ai/tma-1d-store
Chenggang Zhao committed
C
OOB bugs fixed
Chenggang Zhao committed
C
Remove useless STSM
Chenggang Zhao committed
C
Use 1D TMA store
Chenggang Zhao committed
April 10, 2025
C
Make partition pipelined
Chenggang Zhao committed
C
Add CMake support for CLion indexing
Chenggang Zhao committed
April 9, 2025
C
Update roadmap
Chenggang Zhao committed
C
Update roadmap
Chenggang Zhao committed
C
Merge pull request #81 from deepseek-ai/blocktile-256x128
Chenggang Zhao committed
C
Update README
Chenggang Zhao committed
C
Update README
Chenggang Zhao committed
C
Fix indent x2
Chenggang Zhao committed
C
Fix indent
Chenggang Zhao committed
C
Refactor M repetition with loops
Chenggang Zhao committed
C
Larger block N candidates
Chenggang Zhao committed
C
Clean up config heuristics
Chenggang Zhao committed
C
Remove unused x256 WGMMA
Chenggang Zhao committed