add meta impl for int4 preshuffle kernels · pytorch/FBGEMM@cecbb16

Triggered via pull request July 1, 2025 22:34

garroud

synchronize #4384

Status Success

Total duration 51m 30s

Artifacts 2

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_cu12.8.1.whl Expired	620 MB	`sha256:c48c62565417ab01bc8ef2a0b1e53808f518f508d51f1b0e29598d106afe0d39`
fbgemm_gpu_traces_x86_gcc_py3.13_cu12.8.1.zip Expired	5.77 MB	`sha256:e4fde4d1a7f88ef3094614f6db969816de7366c933d6822847861f6f1db3a297`