v4.1 release

This commit is contained in:
Junkai-Wu
2025-07-03 20:07:53 +08:00
committed by GitHub
parent b995f93317
commit a1aaf2300a
155 changed files with 18407 additions and 6068 deletions

View File

@@ -78,11 +78,9 @@ def detect_gpu_arch(prefix):
major, minor = arch
suffix = ""
if major >= 9 and minor >= 0:
if major >= 9:
suffix = "a"
elif minor != 0:
# e.g sm_86, belong with sm_80 family
minor = 0
return f"sm_{major}{minor}{suffix}"