ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-01 12:11:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE]Moe update index (#1672)

Browse Source 
* update MOCK_ID for moe-sorting

* add moe-smoothquant

* update a comment

* fix format

* hot fix

* update topk in overflow case

* update comments

* update bf16 cvt

---------

Co-authored-by: valarLip <340077269@qq.com>
This commit is contained in:
carlushuang
2024-11-25 13:12:35 +08:00
committed by GitHub
parent ce2bdf42a9
commit 36c7ce4e0e
36 changed files with 1321 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
example/ck_tile/14_moe_smoothquant/README.md Normal file
View File

@@ -0,0 +1,15 @@
# moe-smoothquant
This folder contains example for moe-smoothquant using ck_tile tile-programming implementation.
![](misc/moe-sm.png)
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`