Commit Graph

4 Commits

Author SHA1 Message Date
Adam Osewski
b09ce811d5 [rocm-libraries] ROCm/rocm-libraries#5050 (commit 033dad7)
[CK TILE] Skip work if any of Grouped GEMM groups M/N/K are
 zero. (#5050)

## Motivation

It's common in MoE workloads that some experts receive zero tokens,
which would result in some of the dimensions equal to zero. Currently we
handle such case only for non-persistent kernels where we have all GEMMs
information beforehand on host - we validate this during creation of
kernel arguments. However for the "dynamic" input path (persistent
kernel) this information is not available before kernel launch. Thus we
have to validate this during kernel execution. The goal is to add this
validation.

## Technical Details

Skip work if any of Grouped GEMM groups M/N/K are zero for persistent
kernel path.

## Test Plan

Add unit-tests which cover "dynamic" inputs with zero dims for
persistent kernel execution path.

## Test Result

All tests pass.

## Submission Checklist

- [ x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
2026-03-12 13:29:14 +00:00
Aviral Goel
004784ef98 chore(copyright) update library wide CMakeLists.txt copyright header template (#3313)
* chore(copyright) update library wide CMakeLists.txt files copyright header template

* Fix build

---------

Co-authored-by: Sami Remes <samremes@amd.com>
2025-11-28 13:49:54 -08:00
linqunAMD
b0ee317d83 [CK_TILE] Enable ck_tile tests on gfx11 and gfx12 (#2821)
* [CK_TILE] Enable ck_tile test on gfx11 & gfx12

* revert an unnecessary change

* enable pk_int4 on gfx11 & gfx12

* revert .pre-commit-config.yaml
2025-09-12 12:45:14 -07:00
Mateusz Ozga
4cb3d7d7ea Ck tile grouped GEMM example (#1713)
* Ck-tile, impl. grouped gemm

* Workspace is allocated by user, and is passed to the function

* Prepare test to new api design

* Unify GemTransKernelArgs, removing N0 param

* Add 1 to dim3 in paritioner

* Typo: gem - > gemm

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
2024-12-04 21:40:01 +01:00