mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
e116bfef59
* Fix cmake example build
* Support max3 in smoothquant one pass
* support max3 in two pass
* support max3 in add_rmsnorm_rdquant
[ROCm/composable_kernel commit: abae2afc72]
smoothquant
This folder contains example for smoothquant using ck_tile tile-programming implementation.
build
# in the root of ck_tile
mkdir build && cd build
sh ../script/cmake-ck-dev.sh ../ <arch> # you can replace this <arch> to gfx90a, gfx942...
make tile_smoothquant -j
This will result in an executable build/bin/tile_smoothquant
cmdline
args:
-m m dimension (default:3328)
-n m dimension (default:4096)
-v cpu validation or not (default:1)
-prec precision (default:fp16)