docker调用gpu
1、安装gpu驱动
2、安装docker
3、修改docker配置文件
cat /etc/docker/daemon.json
{
"default-runtime": "nvidia",
"runtimes": {
"nvidia": {
"path": "/usr/bin/nvidia-container-runtime",
"runtimeArgs": []
}
},
"exec-opts":["native.cgroupdriver=systemd"]
}
4、安装必要的依赖
yum -y install nvidia-container-runtime nvidia-container-toolkit
5、启动docker
6、启动需要gpu的容器
docker run -itd --name omniparse --gpus all --entrypoint bash -e http_proxy=http://192.168.10.72:7890 -e https_proxy=http://192.168.10.72:7890 -p 8000:8000 savatar101/omniparse:0.1
成功标志
nvidia-smi
Sun Sep 29 10:29:53 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3090 Off | 00000000:1A:00.0 Off | N/A |
| 30% 30C P8 22W / 350W | 4466MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA GeForce RTX 3090 Off | 00000000:1B:00.0 Off | N/A |
| 30% 36C P2 109W / 350W | 24049MiB / 24576MiB | 20% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 2 NVIDIA GeForce RTX 3090 Off | 00000000:1C:00.0 Off | N/A |
| 30% 39C P2 104W / 350W | 15046MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 3 NVIDIA GeForce RTX 3090 Off | 00000000:1D:00.0 Off | N/A |
| 31% 43C P2 105W / 350W | 15046MiB / 24576MiB | 6% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 4 NVIDIA GeForce RTX 3090 Off | 00000000:1E:00.0 Off | N/A |
| 38% 65C P2 340W / 350W | 23228MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 5 NVIDIA GeForce RTX 3090 Off | 00000000:3D:00.0 Off | N/A |
| 35% 57C P2 349W / 350W | 23270MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 6 NVIDIA GeForce RTX 3090 Off | 00000000:3E:00.0 Off | N/A |
| 37% 61C P2 332W / 350W | 23436MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 7 NVIDIA GeForce RTX 3090 Off | 00000000:3F:00.0 Off | N/A |
| 37% 59C P2 332W / 350W | 23354MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 8 NVIDIA GeForce RTX 3090 Off | 00000000:40:00.0 Off | N/A |
| 38% 68C P2 346W / 350W | 24146MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 9 NVIDIA GeForce RTX 3090 Off | 00000000:41:00.0 Off | N/A |
| 36% 60C P2 344W / 350W | 23038MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 108262 C python 4460MiB |
+-----------------------------------------------------------------------------------------+

浙公网安备 33010602011771号