mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00

Files

Satyanvesh Dittakavi 4c57157d50 Do not use warpSize as compile time constant as it is removed (#2320 )

* Do not use warpSize as compile time constant as it is removed

* Update tile_image_to_column_shape.hpp

update warpSize usage.

* clean-up all use of warpSize, make sure code builds

* fix

---------

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
Co-authored-by: Bartlomiej Kocot <barkocot@amd.com>

2025-06-17 11:54:30 -07:00

instances

add fp8 as dst (#1830 )

2025-01-22 17:34:27 +08:00

misc

[CK_TILE]Moe update index (#1672 )

2024-11-25 13:12:35 +08:00

script

add fp8 as dst (#1830 )

2025-01-22 17:34:27 +08:00

CMakeLists.txt

Label CMakeLists message() as DEBUG or STATUS for clean build output (#2301 )

2025-06-10 10:46:47 -07:00

moe_smoothquant.cpp

add fp8 as dst (#1830 )

2025-01-22 17:34:27 +08:00

moe_smoothquant.hpp

Do not use warpSize as compile time constant as it is removed (#2320 )

2025-06-17 11:54:30 -07:00

README.md

[CK_TILE]Moe update index (#1672 )

2024-11-25 13:12:35 +08:00

README.md

moe-smoothquant

This folder contains example for moe-smoothquant using ck_tile tile-programming implementation.

Unlike standard smoothquant op, the input scale is from different expert [expert, hidden], we need reuse the topk-id from previous topk-softmax and select the corresponding expert from current topk, and expand the output/per-token-scale by topk

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_example_moe_smoothquant -j

This will result in an executable build/bin/tile_example_moe_smoothquant