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 6c413ba943 refactor(mge): refactor physical tensor 3 years ago
.github feat(ci): update ci and readme 3 years ago
ci feat(ci): update ci and readme 3 years ago
cmake feat(lite): hidden lar gflags symbols for static link 3 years ago
dnn perf(imperative): specialize convolution implementation 3 years ago
imperative refactor(mge): refactor physical tensor 3 years ago
lite feat(opencl): add OpenCL cache compat level api 3 years ago
scripts fix(imperative): fix use collections error from python3.10 3 years ago
sdk fix(sdk/load_and_run): remove docs of dump_with_testcase_with_mge.py 3 years ago
src fix(megbrain): add rdnn to copybara 3 years ago
test feat(cmake): format all cmake file 3 years ago
third_party feat(mge/third_party): update cutlass version 3 years ago
toolchains feat(cmake): format all cmake file 3 years ago
tools feat(cmake): format all cmake file 3 years ago
.clang-format style(dnn): add bypass of clang-format for dnn foreach_opr macro 3 years ago
.gdbinit feat(dispatch): add gdb debug utils 3 years ago
.gitattributes feat(dnn): differentiate sass kernel with cuda version 3 years ago
.gitignore chroe(.gitignore): add more ignore rules for git 4 years ago
.gitmodules feat(mge): add cpp_redis and tacopie submodule 3 years ago
ACKNOWLEDGMENTS feat(lite): add header licence 3 years ago
CMakeLists.txt feat(dnn): differentiate sass kernel with cuda version 3 years ago
CODE_OF_CONDUCT.md fix typos 4 years ago
CONTRIBUTOR_LICENSE_AGREEMENT.md MegEngine: Initial commit of MegEngine. 5 years ago
LICENSE chore(mge): update copyright years 4 years ago
README.md feat(ci): update ci and readme 3 years ago
README_CN.md feat(ci): update ci and readme 3 years ago
commitlint.config.js ci(copybara): add config files and fix format script 3 years ago
logo.png 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