mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-29 11:16:59 +00:00

Files

juuso-oskari 5a44f5885f WIP(unified_attention): contiguous/non-paged kIsPaged path + non-causal full-range fix

Checkpoint before merging upstream CK. Adds the kIsPaged=false kernel
instances (d64/d128 bf16/fp8, mask/nmask), folds kv_start into base
pointers, and fixes the non-causal KV-range envelope (scan full seq_len
when !FmhaMask::IsMasking instead of the causal horizon).

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-06-08 14:24:05 +00:00

algorithm

[rocm-libraries] ROCm/rocm-libraries#5334 (commit bb5a3c8)

2026-03-20 15:47:22 +00:00

arch

CK-UA: relocate amd_async_global_load_lds_raw to its own header

2026-05-27 13:15:55 +00:00

container

[rocm-libraries] ROCm/rocm-libraries#5921 (commit 032ac1b)

2026-03-30 14:20:20 +00:00

numeric

[rocm-libraries] ROCm/rocm-libraries#5849 (commit d9b89b2)

2026-03-27 20:37:23 +00:00

tensor

WIP(unified_attention): contiguous/non-paged kIsPaged path + non-causal full-range fix

2026-06-08 14:24:05 +00:00

utility

[rocm-libraries] ROCm/rocm-libraries#4469 (commit 0844cb0)

2026-04-01 07:32:36 +00:00

config.hpp

[rocm-libraries] ROCm/rocm-libraries#5088 (commit 36ca523)

2026-03-10 16:47:43 +00:00

README.md

…

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