Merge branch 'develop' of https://github.com/ROCm/composable_kernel into update_cka8w8_uc

1b616990 · aska-0096 · af30d6b6 · 800cf897 · 1b616990 · 1b616990
Commit 1b616990 authored Feb 05, 2025 by aska-0096
20 changed files
--- a/include/ck_tile/ops/epilogue/cshuffle_epilogue.hpp
+++ b/include/ck_tile/ops/epilogue/cshuffle_epilogue.hpp
--- a/include/ck_tile/ops/epilogue/default_2d_epilogue.hpp
+++ b/include/ck_tile/ops/epilogue/default_2d_epilogue.hpp
--- a/include/ck_tile/ops/epilogue/dynamic_quant_epilogue.hpp
+++ b/include/ck_tile/ops/epilogue/dynamic_quant_epilogue.hpp
--- a/include/ck_tile/ops/flatmm.hpp
+++ b/include/ck_tile/ops/flatmm.hpp
--- a/include/ck_tile/ops/flatmm/block/flatmm_32x512x128_1x4x1_16x16x32.hpp
+++ b/include/ck_tile/ops/flatmm/block/flatmm_32x512x128_1x4x1_16x16x32.hpp
--- a/include/ck_tile/ops/flatmm/block/flatmm_sn_32x128x512_1x4x1_16x16x32.hpp
+++ b/include/ck_tile/ops/flatmm/block/flatmm_sn_32x128x512_1x4x1_16x16x32.hpp
--- a/include/ck_tile/ops/flatmm/block/flatmm_sn_32x128x512_1x4x1_16x16x32_itl.hpp
+++ b/include/ck_tile/ops/flatmm/block/flatmm_sn_32x128x512_1x4x1_16x16x32_itl.hpp
--- a/include/ck_tile/ops/flatmm/block/uk/flatmm_sn_uk_gfx9_32x128x512_1x4x1_16x16x16.inc
+++ b/include/ck_tile/ops/flatmm/block/uk/flatmm_sn_uk_gfx9_32x128x512_1x4x1_16x16x16.inc
--- a/include/ck_tile/ops/flatmm/block/uk/flatmm_sn_uk_gfx9_32x128x512_1x4x1_16x16x16_itl.inc
+++ b/include/ck_tile/ops/flatmm/block/uk/flatmm_sn_uk_gfx9_32x128x512_1x4x1_16x16x16_itl.inc
--- a/include/ck_tile/ops/flatmm/block/uk/flatmm_uk_gfx9_32x512x128_1x1x1_16x16x16.inc
+++ b/include/ck_tile/ops/flatmm/block/uk/flatmm_uk_gfx9_32x512x128_1x1x1_16x16x16.inc
--- a/include/ck_tile/ops/fmha.hpp
+++ b/include/ck_tile/ops/fmha.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_appendkv_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_appendkv_kernel.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_kernel.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_kernel.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_tile_partitioner.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_combine_tile_partitioner.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_kernel.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_tile_partitioner.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_tile_partitioner.hpp
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_tile_partitioner.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_tile_partitioner.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_problem.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_problem.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qs_ks_vs.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qs_ks_vs.hpp