Support tuning cache for Cutlass FP8 Grouped GEMM · pytorch/FBGEMM@201eeec

Triggered via pull request June 9, 2025 19:29

cthi

opened #4308

cthi:export-D75889604

Status Success

Total duration 47m 33s

Artifacts 1

fbgemm_gpu_benchmark_cuda.yml

on: pull_request

Matrix: build_artifact

Matrix: benchmark_artifact

Produced during runtime

Name	Size	Digest
fbgemm_gpu_nightly_cuda_x86_gcc_py3.13_cu12.8.0.whl Expired	619 MB	`sha256:b6b7aa3fb85bc1d97c51cb08288335b193c2ed823353ed378240ee9c7009e4f3`