ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-01 20:21:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK TILE GEMM] Support Aquant GEMM with transposeC and preshuffle (#2897)

Browse Source 
* [CK TILE GEMM] Support Aquant GEMM with transposeC and preshuffle

When TransposeC and QuantPreshuffle are both true, Aquant generates
correct result.

* [CK TILE GEMM] Support Aquant GEMM with transposeC and preshuffle

- Add unit tests

* Fix bug in is_quantpreshuffle_enabled

* clang format

---------

Co-authored-by: ThomasNing <thomas.ning@amd.com>
This commit is contained in:
Cong Ma
2025-10-02 12:13:51 -06:00
committed by GitHub
parent a4ab33f539
commit 6fc28ab493
7 changed files with 109 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/ck_tile/ops/gemm_quant/pipeline/tile_gemm_quant_traits.hpp
View File

@@ -39,6 +39,7 @@ template <bool kPadM_,
QuantType QuantType_,
typename AQLayout_ = ALayout_,
typename BQLayout_ = BLayout_,
bool TransposeC_ = false,
bool DoubleSmemBuffer_ = false,
bool UsePersistentKernel_ = false>
struct TileGemmQuantTraits
@@ -62,7 +63,7 @@ struct TileGemmQuantTraits
using AsLayout = ALayout_;
using BsLayout = BLayout_;
static constexpr bool TransposeC = false;
static constexpr bool TransposeC = TransposeC_;
static constexpr bool UseStructuredSparsity = false;
static constexpr index_t NumWaveGroups = 1;
static constexpr bool UsePersistentKernel = UsePersistentKernel_;