ROCm / composable_kernel

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators
https://rocm.docs.amd.com/projects/composable_kernel/en/latest/
Other
251 stars 102 forks source link

Add instances for grouped conv fwd 3d with ConvScale for fp8@bf8->fp8 #1325

Closed geyyer closed 2 weeks ago

geyyer commented 3 weeks ago