mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
Optimized GEMMs for MX FP4/8 (#2294)
Adds V3 GEMM pipeline for MX FP4 and MX FP8 Adds V3 GEMM pipeline for MX FP4 with preshuffling Adds MXFP4 GEMM tests (#2275) Adds MXFP4 GEMM examples Adds MXFP4 GEMMs to ckProfiler Co-authored-by: Andriy Roshchenko <107577548+andriy-ca@users.noreply.github.com> Co-authored-by: Andriy Roshchenko <andriy.roshchenko@amd.com> Co-authored-by: aska-0096 <haocwang@amd.com> Co-authored-by: lalala-sh <Jiaxing.Wen@amd.com> Co-authored-by: OscarXu <huaiguxu@amd.com> Co-authored-by: mtgu0705 <mtgu@amd.com> Co-authored-by: Ding, Yi <yi.ding@amd.com> Co-authored-by: feifei14119 <feiw@amd.com> Co-authored-by: Lin, Qun <qlin@amd.com> Co-authored-by: joye <joye@amd.com> Co-authored-by: Rostyslav Geyyer <46627076+geyyer@users.noreply.github.com>
This commit is contained in:
committed by
GitHub
parent
233e274077
commit
00247e3c29
@@ -112,7 +112,7 @@ struct UniversalFlatmmPipelineAgBgCrPolicy
|
||||
make_tuple(number<kKPerBlock / kKPack>{}, number<kKPack>{}))),
|
||||
make_tuple(sequence<1, 0>{}, sequence<2, 3>{}),
|
||||
make_tuple(sequence<0>{}, sequence<1>{}));
|
||||
return a_lds_block_desc;
|
||||
return a_lds_block_desc;
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user