composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 10:09:41 +00:00

Files

Mingtao Gu 6fb0e00df5 Added Int4 mixed batch gemm support (#1839 )

* remove redundant kernels.

* added batched_gemm_xdl_fp16int4_b_scale_v3

* Enabled the split K.

* added the batched_gemm_b_scale ckProfiler, meet function issue

* fix some typo

* fix ckProfiler build issue

* fix some bugs

* updated some debug info

* comment some code

* Fix

* fixed some bugs and refactor the code

* fixed a function bug.

* formatted files.

* formatted

* uncommented the ckProfiler CMakeLists

* fixed.

* fix ckProfiler for batched_gemm_b_scale

---------

Co-authored-by: mtgu0705 <mtgu@amd.com>
Co-authored-by: aska-0096 <haocwang@amd.com>
Co-authored-by: Bartlomiej Kocot <barkocot@amd.com>

[ROCm/composable_kernel commit: d9f1ead347]

2025-02-10 11:17:02 +08:00

batched_gemm_xdl_bf16_v3.cpp

Add SplitK support into Batched GEMM V3 (#1729 )

2024-12-13 21:08:35 +01:00

batched_gemm_xdl_bf16.cpp

Refactoring cmake files to build data types separately. (#932 )

2023-09-20 22:15:56 -07:00

batched_gemm_xdl_fp8_rowwise_v3.cpp

Batched GEMM Multiple D based on Universal GEMM (#1655 )

2024-11-18 14:03:45 +01:00

batched_gemm_xdl_fp16.cpp

Refactor device op implementations into impl subdirectory. (#420 )