Skip to content

Support bf16 in blackwell cutlass decode attention kernel #6063

Support bf16 in blackwell cutlass decode attention kernel

Support bf16 in blackwell cutlass decode attention kernel #6063

Re-run triggered September 23, 2025 02:44
Status Success
Total duration 2h 1m 12s
Artifacts 2
generate-matrix  /  generate
7s
generate-matrix / generate
filter-matrix
6s
filter-matrix
Matrix: build
Fit to window
Zoom out
Zoom in

Annotations

1 warning
filter-matrix
The `python-version` input is not set. The version of Python currently in `PATH` will be used.

Artifacts

Produced during runtime
Name Size Digest
pytorch_FBGEMM__3.10_cu126_aarch64
13.9 MB
sha256:2afcdf2abec89d640c6c07703a9c1658f35849d650f3532c8a96fa2b3dbd614d
pytorch_FBGEMM__3.10_cu128_aarch64
42.5 MB
sha256:5b588aee493b8ff8dcd99892ca30f90600a90e1f19828478cf43bcba93b1cc3b