merge develop to attn-train-develop-qloop

76f2b6cd · danyao12 · 9b4c780a · 1ee99dca · 76f2b6cd · 76f2b6cd
Commit 76f2b6cd authored Jul 14, 2023 by danyao12
20 changed files
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
--- a/example/15_grouped_gemm/run_grouped_gemm_example.inc
+++ b/example/15_grouped_gemm/run_grouped_gemm_example.inc
--- a/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
+++ b/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
--- a/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_bf16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_mean_meansquare_xdl_fp32.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_reduce_xdl_common.hpp
--- a/example/17_convnd_bwd_data/CMakeLists.txt
+++ b/example/17_convnd_bwd_data/CMakeLists.txt
--- a/example/17_convnd_bwd_data/convnd_bwd_data_common.hpp
+++ b/example/17_convnd_bwd_data/convnd_bwd_data_common.hpp