Skip to content

[Kernel] conv2d: 8-wave double-buffered implicit-GEMM BF16 kernel(gfx950)#733

Open
jiacao-amd wants to merge 6 commits into
ROCm:mainfrom
jiacao-amd:jiacao/conv2d-implicit-mfma
Open

[Kernel] conv2d: 8-wave double-buffered implicit-GEMM BF16 kernel(gfx950)#733
jiacao-amd wants to merge 6 commits into
ROCm:mainfrom
jiacao-amd:jiacao/conv2d-implicit-mfma

conv2d: dedup _run_compiled by importing from kernels.tensor_shim

cbaa3cd
Select commit
Loading
Failed to load commit list.
Sign in for the full log view