Merge remote-tracking branch 'origin/develop' into aosewski/ggemm_multi_d2

036c5234 · Adam Osewski · 22995e9a · 7843a8a7 · 036c5234 · 036c5234
Commit 036c5234 authored May 14, 2024 by Adam Osewski
20 changed files
--- a/include/ck_tile/ops/fmha.hpp
+++ b/include/ck_tile/ops/fmha.hpp
--- a/include/ck_tile/ops/fmha/block/block_attention_bias_enum.hpp
+++ b/include/ck_tile/ops/fmha/block/block_attention_bias_enum.hpp
--- a/include/ck_tile/ops/fmha/block/block_position_encoding.hpp
+++ b/include/ck_tile/ops/fmha/block/block_position_encoding.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/pipeline/block_fmha_pipeline_enum.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_enum.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_qr_ks_vs.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qr_ks_vs.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qr_ks_vs_async.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qr_ks_vs_async.hpp
--- a/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qr_ks_vs_fp8.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/block_fmha_pipeline_qr_ks_vs_fp8.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
--- a/include/ck_tile/ops/fmha/pipeline/tile_fmha_traits.hpp
+++ b/include/ck_tile/ops/fmha/pipeline/tile_fmha_traits.hpp
--- a/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
+++ b/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_multi_abd.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_multi_abd.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_xdl_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_xdl_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_bilinear_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_bilinear_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_xdl.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_xdl.inc
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multi_abd_fixed_nk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multi_abd_fixed_nk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop.hpp