ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-26 08:00:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add the last two forward instance traits. (#3134)

Browse Source 
* Add InstanceTraits for DeviceGroupedConvFwdMultipleD_Wmma_CShuffle

* Add InstanceTraits for kernel_grouped_conv_fwd_dl_multiple_d

* A few small changes to fix broken instance traits.

[ROCm/composable_kernel commit: 5ed2046bee]
This commit is contained in:
John Shumway
2025-10-31 07:52:42 -07:00
committed by GitHub
parent d2474f5396
commit a8a377ca53
17 changed files with 1207 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
View File

@@ -1760,6 +1760,8 @@ struct FastNumericArrayConverter<uint8_t, half_t, N>
struct DynamicUnaryOp
{
static constexpr const char* name = "DynamicUnaryOp";
__host__ __device__ DynamicUnaryOp() = delete;
__host__ __device__ DynamicUnaryOp(const Swish& swish)