yinglu 3f44e675e4 TF32 POC in Conv3d on MI30x platform #2763 (second attempt) (#2852) ...

* Revert "Revert "feature:tf32:add initial conv3d fwd kernel support (#2763)" (#2848)"

This reverts commit 82da15ffa430a297fb072d0a15b3ada5753f69b1.

* fix compile error on gf12x

* only run tf32 example on gfx942

* only build tf32 instance on gfx942

* ckProfiler:only support tf32 in gfx942

* delete unuseful messages

[ROCm/composable_kernel commit: dd7af118d7]

2025-09-17 14:50:15 -07:00

..

gpu

TF32 POC in Conv3d on MI30x platform #2763 (second attempt) (#2852)

2025-09-17 14:50:15 -07:00

operator_transform

Add padding to 1x1Stride1Pad0 conv specialization (grouped conv bwd weight) (#2675)

2025-08-14 00:21:09 +02:00