Merge branch 'develop' into codegen-enable-hiprtc

2a30cfdd · arai713 · GitHub · 9533a172 · 78195ccc · 2a30cfdd
Unverified Commit 2a30cfdd authored Feb 12, 2025 by arai713 Committed by GitHub Feb 12, 2025
20 changed files
--- a/include/ck_tile/ops/elementwise.hpp
+++ b/include/ck_tile/ops/elementwise.hpp
--- a/include/ck_tile/ops/elementwise/unary_element_wise_operation.hpp
+++ b/include/ck_tile/ops/elementwise/unary_element_wise_operation.hpp
--- a/include/ck_tile/ops/epilogue.hpp
+++ b/include/ck_tile/ops/epilogue.hpp
--- 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