From 6c801269fb3f4ba79eb3bef35c79aba01abd2695 Mon Sep 17 00:00:00 2001 From: John Afaganis Date: Thu, 18 Dec 2025 23:02:42 -0700 Subject: [PATCH] Minor CHANGELOG.md correction (#3451) Address a minor issue where the changelog entry for #3423 was accidentally added to the wrong section. [ROCm/composable_kernel commit: b188a2a89682f124d5adbe4469226f3a680eec1c] --- CHANGELOG.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6229e0fd6b..addb4ce4f0 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -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.