ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-15 18:42:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'b188a2a89682f124d5adbe4469226f3a680eec1c' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-12-19 06:16:38 +00:00
parent 0779609ddc
commit 494dd1813f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.md
View File

@@ -8,7 +8,8 @@ Documentation for Composable Kernel available at [https://rocm.docs.amd.com/proj
* Added support for explicit GEMM in CK_TILE grouped convolution forward and backward weight.
* Added TF32 convolution support on gfx942 and gfx950 in CK. It could be enabled/disabled via `DTYPES` of "tf32".
* Added attention sink support for FMHA FWD, include qr_ks_vs, qr_async and splitkv pipelines.
* Added support for microscaling (MX) FP8/FP4 mixed data types to Flatmm pipeline
* Added support for microscaling (MX) FP8/FP4 mixed data types to Flatmm pipeline.
* Added support for fp8 dynamic tensor-wise quantization of fp8 fmha fwd kernel.
### Changed
@@ -17,7 +18,6 @@ Documentation for Composable Kernel available at [https://rocm.docs.amd.com/proj
## Composable Kernel 1.2.0 for ROCm 7.2.0
### Added
* Added support for fp8 dynamic tensor-wise quantization of fp8 fmha fwd kernel.
* Added support for bf16 data type to grouped_gemm and grouped_gemm_preshuffle.
* Added Col-Col-Row-Col layout support for aquant mode in blockscale GEMM.
* Added support for mixed precision fp8 x bf8 universal GEMM and weight preshuffle GEMM.