mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-11 17:00:18 +00:00

Files

Cong Ma 82890192dd [CK TILE] Support fp8/fp16 with pk_int4_t as data types for tensors A and B (#2805 )

- Add support for tensor A/B in both fp16+pk_int4_t and fp8+pk_int4_t formats
- Implement A(bf8) B(i4) support in universal GEMM
- Use new implementation for i4 to fp8 conversion in Block Scale

2025-09-09 16:40:52 -07:00

algorithm

refactor: use snake_case naming in ck_tile/core components (#2766 )

2025-09-03 09:34:11 +02:00

arch

[CK_TILE] FMHA avoid unnecessary vmcnt0 (#2715 )

2025-08-25 20:55:12 +08:00

container

[CK_TILE] Add permuteN optimization to remove lds operation in c_shuffle (#2764 )

2025-09-08 22:02:48 -07:00

numeric

[CK TILE] Support fp8/fp16 with pk_int4_t as data types for tensors A and B (#2805 )

2025-09-09 16:40:52 -07:00

tensor

[CK_TILE] Implement Row/Col quant grouped gemm (#2786 )

2025-09-08 10:25:57 -07:00

utility

[Util] add a RAII stuct which inserts markers into generated asm (#2748 )

2025-09-08 22:02:02 -07:00

config.hpp

Fix formatting problem (#2768 )

2025-09-02 14:14:10 +03:00

README.md

introducing ck_tile! (#1216 )

2024-04-15 19:27:12 -05:00

README.md

ck_tile/core

ck_tile/core contains every basic functions and structures to create a GPU kernel using ck_tile. User should only include ck_tile/core.hpp this single header to use all the functionality. Everything is under ck_tile namespace. The coding style under this folder should be similar to std (snake_case for structure/function, Camel for template types...)

algorithm/
    coordinate transform and some other reusable algorithm
arch/
    contains some basic device building block like mma, buffer addressing, etc...
container/
    contains basic container data structure, array/sequence/tuple/...
numeric/
    data type, and data type related math
tensor/
    tensor descriptors and tile level API
utility/
    other utility function for both host/device