Add NEON implementation of Fused8BitRowwiseQuantizedSBFloatToFloatOrHalf #9272
facebook-github-botbuild_wheels_linux_aarch64.yml
on: pull_request
generate-matrix
/
generate
6s
Matrix: build
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
pytorch_FBGEMM__3.9_cpu_aarch64
|
2.76 MB |
|
|
pytorch_FBGEMM__3.9_cu126_aarch64
|
446 MB |
|
|
pytorch_FBGEMM__3.9_cu128_aarch64
|
450 MB |
|