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 afe9c4b50d feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
..
arch_mappings.h feat(dnn/cuda): integrate cutlass operation table and replace all cutlass wrappers 3 years ago
convolution_operation.h feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
gemm_operation.h style(all): reformat c++ code 3 years ago
initialize_all.cu feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
library.h feat(dnn/cuda): add implicit bmm large kernel dwconv2d fprop impl 3 years ago
library_internal.h feat(dnn/cuda): add implicit bmm large kernel dwconv2d fprop impl 3 years ago
manifest.cpp feat(dnn/cuda): integrate cutlass operation table and replace all cutlass wrappers 3 years ago
manifest.h style(all): reformat c++ code 3 years ago
operation_table.cpp feat(dnn/cuda): add implicit bmm large kernel dwconv2d fprop impl 3 years ago
operation_table.h feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
singleton.cu feat(dnn/cuda): integrate cutlass operation table and replace all cutlass wrappers 3 years ago
singleton.h feat(dnn/cuda): integrate cutlass operation table and replace all cutlass wrappers 3 years ago
util.cu feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
util.h style(all): reformat c++ code 3 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