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 3f5238fb38 feat(mgb/dnn): add accuracy shake checker 4 years ago
..
chanwise chore(mge): update copyright years 4 years ago
int8 feat(dnn/cuda): add deconv int8 and fix cutlass conv wrapper base on modify cutlass 2.4 4 years ago
int8_imma feat(dnn/cuda): add deconv int8 and fix cutlass conv wrapper base on modify cutlass 2.4 4 years ago
matmul chore(mge): update copyright years 4 years ago
quint4x4x32_wmma chore(mge): update copyright years 4 years ago
algo.cpp feat(log): opt log 4 years ago
algo.h feat(mgb/dnn): add accuracy shake checker 4 years ago
batched_matmul.cpp fix(megdnn): some fixes of execution policy 4 years ago
bfloat16.cpp refactor(megdnn): refactor sub opr setter 4 years ago
chanwise.cpp chore(mge): update copyright years 4 years ago
chanwise_8x8x32.cpp chore(mge): update copyright years 4 years ago
chanwise_small.cpp chore(mge): update copyright years 4 years ago
conv_bias_int8.cuh chore(mge): update copyright years 4 years ago
conv_nchwqs8.cpp fix(dnn/cuda): add cuda nchw int8 conv impl with nchw4 to fix cu111 compatibility 4 years ago
cudnn_conv.cpp chore(mge): update copyright years 4 years ago
cudnn_conv_bias_activation.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
cutlass_convolution_wrapper.cu feat(dnn/cuda): add deconv int8 and fix cutlass conv wrapper base on modify cutlass 2.4 4 years ago
cutlass_convolution_wrapper.cuh fix(mgb/gopt): fix folding conv dimshuffle opt pass 4 years ago
group_conv.cpp fix(megdnn): some fixes of execution policy 4 years ago
helper.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
helper.h feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_chwn4_dp4a.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_chwn4_imma.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_chwn4_imma_reorder_filter.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_chwn4_imma_unroll_width.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_nchw4_dp4a.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_nchw4_imma.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
implicit_gemm_int8_nchw32_imma.cpp feat(mgb/dnn): add accuracy shake checker 4 years ago
inplace_matmul.cpp chore(mge): update copyright years 4 years ago
matmul.cpp refactor(megdnn): refactor sub opr setter 4 years ago
matmul_8x8x32.cpp chore(mge): update copyright years 4 years ago
opr_impl.cpp refactor(mgb/dnn): add negative attribute for algo 4 years ago
opr_impl.h refactor(mgb/dnn): add negative attribute for algo 4 years ago
quint4x4x32_wmma.cpp chore(mge): update copyright years 4 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