ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-07 08:15:04 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
881bc3fbb03b8fb810699773679c5b14bc99bcbc
composable_kernel/include/ck/tensor_operation/gpu
History
Anton Gorenko 9912e5f09c Add a special wrapper to use DeviceGemmMultipleD_Wmma_CShuffleV3 with old API 
ckProfiler uses DeviceGemmMultipleD (tests also call its functions), the wrapper allows to use
DeviceGemmMultipleDSplitK instances there.
2025-06-04 12:34:26 +05:00
..
block
WMMA GEMM universal pipeline v1, mixed precision and paddings, examples (#2230)
2025-06-04 12:22:33 +06:00
device
Add a special wrapper to use DeviceGemmMultipleD_Wmma_CShuffleV3 with old API
2025-06-04 12:34:26 +05:00
element
Add Clamp/Relu bf16/fp16 cast fixes (#2279)
2025-06-03 18:31:46 +02:00
grid
Implement DeviceGemmMultipleD_Wmma_CShuffleV3
2025-06-04 12:29:34 +05:00
thread
Moe gemm activation (#2026)
2025-04-23 10:35:34 +08:00
warp
Use new mfma instructions for FP8 on gfx950 (#2202)
2025-05-19 17:29:51 -07:00