You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
Megvii Engine Team 00ef677249 fix(mgb): remove internal for cambricon and atlas 4 years ago
..
aarch64 feat(dnn/arm): add fp32 asm gemm for a53 a55 and i8i8i16 gemm for a72 a53 4 years ago
arm_common feat(dnn/arm): add fp32 asm gemm for a53 a55 and i8i8i16 gemm for a72 a53 4 years ago
armv7 feat(dnn): make mk4 and mk8 matmul for winograd both on aarch64 and armv7 supports n=1 4 years ago
atlas fix(mgb): remove internal for cambricon and atlas 4 years ago
cambricon fix(mgb): remove internal for cambricon and atlas 4 years ago
common feat(dnn/cuda): integrate cutlass nchw32 tensorcore convolution 4 years ago
cpu feat(dnn/test): split cpu.convolution 5 years ago
cuda feat(dnn/cuda): integrate cutlass nchw32 tensorcore convolution 4 years ago
dispatcher feat(dnn/naive): support weight preprocess interface in dnn 5 years ago
fallback fix(dnn/fallback): fix conv1x1/im2col usable and fuse-conv-bias get fp32xfp32-->qint8 error 5 years ago
naive fix(dnn/naive): add convolution nchw44-dot format 5 years ago
x86 feat(dnn/arm): add fp32 asm gemm for a53 a55 and i8i8i16 gemm for a72 a53 4 years ago
CMakeLists.txt fix(mgb): remove internal for cambricon and atlas 4 years ago
gtest_main.cpp MegEngine: Initial commit of MegEngine. 5 years ago
main.cpp MegEngine: Initial commit of MegEngine. 5 years ago

MegEngine 安装包中集成了使用 GPU 运行代码所需的 CUDA 环境,不用区分 CPU 和 GPU 版。 如果想要运行 GPU 程序,请确保机器本身配有 GPU 硬件设备并安装好驱动。 如果你想体验在云端 GPU 算力平台进行深度学习开发的感觉,欢迎访问 MegStudio 平台

C++ Cuda Python C SVG other