issues
search
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 functional support of AB group scale
#1345
Open
zjing14
opened
2 weeks ago
zjing14
commented
2 weeks ago
Added grid/device ops for AB group scale
Added an example for fp8
jianyuh
commented
2 weeks ago
CC @jwfromm