DeepSeek/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM synced 2025-04-17 01:31:15 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix type lint

Browse Source
This commit is contained in:
Chenggang Zhao 2025-03-10 13:10:16 +08:00
parent ba1e93a5c7
commit 5e4badc577
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
deep_gemm/jit_kernels/gemm.py
View File

@ -56,7 +56,7 @@ def get_smem_size(num_stages: int, k: int, block_m: int, block_n: int, block_k:
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, int]: is_grouped_contiguous: bool = False) -> Tuple[int, int, int, int, int, int]:
if not is_grouped_contiguous: if not is_grouped_contiguous:
# TODO: for some cases, smaller M block is better, add them into tuning space # TODO: for some cases, smaller M block is better, add them into tuning space
block_ms = (64 if m <= 64 else 128, ) block_ms = (64 if m <= 64 else 128, )