ROCm/composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 09:16:52 +00:00

Files

History

Xiao Li bac51b6ec0 Fix amd_ck_fp8.hpp macro definitions (#2325 )

* Fix amd_ck_fp8.hpp macro definitions

1. Define CK_USE_FNUZ_FP8 and CK_USE_OCP_FP8 definitions only if they were not defined before.
2. Prefix __assert_fnuz_support and __assert_ocp_support with namespace
   fp8_impl to avoid redefined error when building with rocm 6.4+
   (rocm/6.4.0/include/hip/amd_detail/amd_hip_fp8.h)


Co-authored-by: Andriy Roshchenko <andriy.roshchenko@amd.com>

2025-06-24 22:46:15 -06:00

..

enable gfx115x support (#2065 )

2025-04-09 10:06:42 -07:00

library/utility

Improve fmha_bwd tests performance (#2376 )

2025-06-24 07:45:24 -07:00

problem_transform

update copyright headers (#726 )

2023-05-31 18:46:57 -05:00

Jing's contribution: prototype of mixed precision gemm FP16/BF16xint4 GEMM (#1762 )

2025-01-02 11:48:06 +08:00

tensor_description

Optimize grouped conv bwd weight for small M and N (#1303 )

2024-05-22 21:01:01 +02:00

tensor_operation

Implement batched gemm wmma (RDNA batched gemm) based on wmma cshuffle v3 (#2319 )

2025-06-24 07:28:13 -07:00

Fix amd_ck_fp8.hpp macro definitions (#2325 )

2025-06-24 22:46:15 -06:00

Fix warnings during wrapper docs generation (#1192 )

2024-03-08 17:13:03 -08:00

ck.hpp

Do not use warpSize as compile time constant as it is removed (#2320 )

2025-06-17 11:54:30 -07:00

config.h.in

DeviceGemm_Wmma_CShuffleV3 with BlockGemmPipelineVersion::v3 (#2096 )

2025-04-28 10:14:21 +05:00

filesystem.hpp

Customize filesystem in CK for legacy systems (#1509 )

2024-09-13 07:51:07 -07:00

README.md

Add Grouped Convolution and GEMM documentation (#1719 )

2025-02-04 16:41:49 +01:00

stream_config.hpp

Universal gemm flush cache (#1251 )

2024-04-25 15:07:14 -05:00

version.h.in

[HotFix] add config and version files to pass on build info (#856 )

2023-08-23 11:36:17 -07:00

README.md

Back to the main page

Composable Kernel supported operations

Supported device operations