DeepSeek/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM synced 2025-06-26 23:15:49 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Less stages for small shape K

Browse Source
This commit is contained in:
Chenggang Zhao
2025-04-28 10:36:08 +08:00
parent 86afd0c212
commit d374456787
2 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deep_gemm/jit_kernels/gemm.py
View File

@@ -130,7 +130,7 @@ def get_best_configs(m: int, n: int, k: int, num_groups: int, num_sms: int,
# Always pick the longest one
# NOTES: for double B scales, the best number of stages may be reduced
best_num_stages, best_smem_config, sm90_capacity = None, None, 232448
stage_candidates = (8, 7, 6, 5, 4, 3)
stage_candidates = tuple(filter(lambda s: s <= k // 128, (8, 7, 6, 5, 4, 3)))
if 128 % best_block_n != 0 and 128 // math.gcd(128, best_block_n) <= 4:
# Unrolling both stages and `num_former_iters` will cause large code size
stage_candidates = (4, 3)