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 cf1db2616e fix(fastrun): replace py_redis with cpp_redis to avoid deadlock 3 years ago
..
amp feat(dnn/check_non_finite): addmul scale to check_non_finite opr 3 years ago
autodiff docs(docstring): transfer to google style 3 years ago
core fix(mge/elwise): removed back to fp32 mode 3 years ago
data feat(imperative): mge hub pretrained support s3 3 years ago
distributed Merge pull request #407 from ShrimpLau:docstring_all_reduce_xxx 3 years ago
dtr fix(imperative): release dtr related resources when disable dtr 3 years ago
experimental feat(traced_module): move traced_module out of the experimental folder 3 years ago
functional feat(dnn/check_non_finite): addmul scale to check_non_finite opr 3 years ago
hub feat(imperative): mge hub pretrained support s3 3 years ago
jit feat(mge): support dump with specific format 3 years ago
module test(imperative/python): fix testcase for magicmind runtime module 3 years ago
optimizer fix(mge/optimizer): allow lr to be 0 3 years ago
quantization docs(imperative): fix multiple target warning when cross-reference 3 years ago
random feat(mge/uniform): add the judgment of low and high 3 years ago
tools feat(imperative): add more tools for megengine 3 years ago
traced_module fix(traced_module): fix tensor node init 3 years ago
utils fix(fastrun): replace py_redis with cpp_redis to avoid deadlock 3 years ago
__init__.py fix(fastrun): replace py_redis with cpp_redis to avoid deadlock 3 years ago
config.py fix(mge): control compute_mode by context 3 years ago
conftest.py ci(pytest): fixture doctest namespace in pytest config 3 years ago
device.py feat(cuda/comp_node): gets (maximum) GPU memory allocated/reserved 3 years ago
logger.py fix(mge): fix some minor problems 3 years ago
serialization.py docs(docstring): transfer to google style 3 years ago
tensor.py docs(docstring): transfer to google style 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