mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-31 11:56:44 +08:00
23 lines
534 B
Markdown
23 lines
534 B
Markdown
# FastDeploy environment requirements
|
||
|
||
## System Platform
|
||
|
||
- Linux x64/aarch64
|
||
- Windows 10 x64
|
||
- Mac OSX (x86 10.0+ / arm64 12.0+)
|
||
|
||
## Hardware Dependencies
|
||
|
||
- Intel CPU
|
||
- Nvidia GPU
|
||
|
||
## Software Dependencies
|
||
|
||
- cmake >= 3.12
|
||
- gcc/g++ >= 8.2
|
||
- python >= 3.6
|
||
- Visual Studio 2019 (Windows)
|
||
- cuda >= 11.0 （The default installation path of Linux is under /usr/local/cuda）
|
||
- cudnn >= 8.0
|
||
- TensorRT、Paddle Inference、ONNXRuntimeand other inference engines will be included in the SDK and do not need to be installed separately.
|