8000 [cutlass backend] Minor lru_cache to slightly speed up filtering ops (#152577) · pytorch/pytorch@1fef3cd · GitHub
[go: up one dir, main page]
Skip to content

[cutlass backend] Minor lru_cache to slightly speed up filtering ops …

Sign in for the full log view
unit-test / cuda12.6-py3.12-gcc9-sm86 / test (inductor, 1, 2, ephemeral.linux.g5.4xlarge.nvidia.gpu)
succeeded May 2, 2025 in 2h 9m 7s
0