Docker Desktop for Windows 中的 GPU 支持

目录

注意

目前，Docker Desktop 中的 GPU 支持仅在具有 WSL2 后端的 Windows 上可用。

Docker Desktop for Windows 支持 NVIDIA GPU 上的 NVIDIA GPU 半虚拟化 (GPU-PV)，允许容器访问 GPU 资源，用于 AI、机器学习或视频处理等计算密集型工作负载。

前提条件

要启用 WSL 2 GPU 半虚拟化，你需要

验证 GPU 支持

为确认 GPU 在 Docker 内部正常工作，请运行以下命令

$ docker run --rm -it --gpus=all nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -gpu -benchmark

这将在 GPU 上运行 n-body 模拟基准测试。输出将类似于

Run "nbody -benchmark [-numbodies=<numBodies>]" to measure performance.
        -fullscreen       (run n-body simulation in fullscreen mode)
        -fp64             (use double precision floating point values for simulation)
        -hostmem          (stores simulation data in host memory)
        -benchmark        (run benchmark to measure performance)
        -numbodies=<N>    (number of bodies (>= 1) to run in simulation)
        -device=<d>       (where d=0,1,2.... for the CUDA device to use)
        -numdevices=<i>   (where i=(number of CUDA devices > 0) to use for simulation)
        -compare          (compares simulation results running once on the default GPU and once on the CPU)
        -cpu              (run n-body simulation on the CPU)
        -tipsy=<file.bin> (load a tipsy model file for simulation)

> NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

> Windowed mode
> Simulation data stored in video memory
> Single precision floating point simulation
> 1 Devices used for simulation
MapSMtoCores for SM 7.5 is undefined.  Default to use 64 Cores/SM
GPU Device 0: "GeForce RTX 2060 with Max-Q Design" with compute capability 7.5

> Compute 7.5 CUDA device: [GeForce RTX 2060 with Max-Q Design]
30720 bodies, total time for 10 iterations: 69.280 ms
= 136.219 billion interactions per second
= 2724.379 single-precision GFLOP/s at 20 flops per interaction

运行真实模型：使用 Ollama 运行 Llama2

使用官方 Ollama 镜像运行 Llama2 LLM 并启用 GPU 加速

$ docker run --gpus=all -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

然后启动模型

$ docker exec -it ollama ollama run llama2
页面选项