Zhean Xu 919f55be9c Support unaligned n,k and gmem stride

2025-05-09 12:55:46 +08:00

..

__init__.py

Init weight gradient kernels.

2025-05-06 17:16:27 +08:00

gemm.py

Support unaligned n,k and gmem stride

2025-05-09 12:55:46 +08:00

m_grouped_gemm.py

Refactor JIT compilation (+NVRTC support) (#94)

2025-05-07 11:38:14 +08:00

runtime.py

Merge branch 'main' into wgrad-gemm

2025-05-09 12:30:13 +08:00

tuner.py

Add DG_PRINT_AUTOTUNE to README

2025-05-07 11:46:52 +08:00

utils.py

Fix get_col_major_tma_aligned_tensor to handle 2-dimensional inputs

2025-03-13 22:15:16 +08:00

wgrad_gemm.py

Merge branch 'main' into wgrad-gemm

2025-05-09 12:30:13 +08:00