Merge branch 'develop' into gemm_v2r3_kpad_fix

a8629a98 · zjing14 · GitHub · 8dc713ea · 94bfa502 · a8629a98
Unverified Commit a8629a98 authored Sep 26, 2023 by zjing14 Committed by GitHub Sep 26, 2023
20 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_fastgelu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_add_relu_add_layernorm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_fastgelu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f8_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f8_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f8_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f8_f16_f16_km_nk_mn_instance.cpp