20250201 - Ollama Docker镜像使用指南 - ollama- Docker Image Docker Hub¶

分类: Clippings
创建: 2025-02-01
标签: Ollama, Docker, 语言模型, 本地运行, GPU支持

ollama/ollama - Docker Image | Docker Hub¶

摘要 (Summary)¶

Ollama是一个便于在本地运行大型语言模型的Docker镜像。它支持CPU、Nvidia GPU以及AMD GPU，并提供相应的安装和配置说明。用户可以通过简单的命令启动模型并尝试不同的模型。

要点 (Key Facts)¶

Ollama Docker镜像，支持CPU和GPU。
安装NVIDIA Container Toolkit和配置Docker使用Nvidia驱动。
使用AMD GPU时的指令。
可以在本地运行模型，例如llama3。

正文 (Content)¶

Ollama Docker image¶

Ollama⁠ makes it easy to get up and running with large language models locally.

CPU only¶

docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

Nvidia GPU¶

Install the NVIDIA Container Toolkit⁠.

Install with Apt

Configure the repository

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
    | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
    | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
    | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update

Install the NVIDIA Container Toolkit packages

sudo apt-get install -y nvidia-container-toolkit

Install with Yum or Dnf

Configure the repository

curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo \
    | sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo

Install the NVIDIA Container Toolkit packages

sudo yum install -y nvidia-container-toolkit

Configure Docker to use Nvidia driver

sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

Start the container

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

==RUN the docker container securely Completely local, isolated from the rest of the OS==:

docker run -d --gpus all -v ollama:/root/.ollama -p 11434:11434 --security-opt=no-new-privileges --cap-drop=ALL --cap-add=SYS_NICE --memory=8g --memory-swap=8g --cpus=4 --read-only --name ollama ollama/ollama

AMD GPU¶

To run Ollama using Docker with AMD GPUs, use the rocm tag and the following command:

docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:rocm

Run model locally¶

Now you can run a model:

docker exec -it ollama ollama run llama3

Try different models¶

More models can be found on the Ollama library⁠.

Learn more¶

https://github.com/ollama/ollama⁠