DeepSeek/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM synced 2025-05-05 19:34:22 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Code format

Browse Source
This commit is contained in:
Chenggang Zhao 2025-04-07 09:32:43 +08:00
parent 3ea3cb203c
commit bff5724ded
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
deep_gemm/jit_kernels/gemm.py
View File

@ -67,6 +67,7 @@ def get_smem_size(num_stages: int, k: int, block_m: int, block_n: int, block_k:
smem_size += smem_barrier smem_size += smem_barrier
return smem_size return smem_size
@lru_cache(maxsize=None) @lru_cache(maxsize=None)
def get_best_configs(m: int, n: int, k: int, num_groups: int, num_sms: int, def get_best_configs(m: int, n: int, k: int, num_groups: int, num_sms: int,
is_grouped_contiguous: bool = False) -> Tuple[int, int, int, int, Tuple[int, bool], int]: is_grouped_contiguous: bool = False) -> Tuple[int, int, int, int, Tuple[int, bool], int]: