mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 16:48:03 +08:00
23 lines
448 B
Markdown
23 lines
448 B
Markdown
# FastDeploy环境要求
|
||
|
||
## 系统平台
|
||
|
||
- Linux x64/aarch64
|
||
- Windows 10 x64
|
||
- Mac OSX (x86 10.0以上/ arm64 12.0以上)
|
||
|
||
## 硬件
|
||
|
||
- Intel CPU
|
||
- Nvidia GPU
|
||
|
||
## 软件
|
||
|
||
- cmake >= 3.12
|
||
- gcc/g++ >= 8.2
|
||
- python >= 3.6
|
||
- Visual Studio 2019 (Windows平台)
|
||
- cuda >= 11.0 (Linux默认安装路径在/usr/local/cuda下)
|
||
- cudnn >= 8.0
|
||
- TensorRT、Paddle Inference、ONNXruntime等推理引擎,会在SDK中包含,不需要单独安装。
|