基于龙蜥anolis在gpu上通过docker手动编译部署ollama

一、安装dockeryum install docker二、下载docker镜像docker pull registry.openanolis.cn/openanolis/anolisos:23.4三、编写Docker filevim DockerfileFROM registry.openanolis.cn/openanolis/anolisos:23.4 MAINTAINER wangchaodongwang479961270vip.qq.com ARG ARCHx86_64 ARG VERSIONv0.17.7 ENV CUDA_HOME/usr/local/cuda ENV PATH${CUDA_HOME}/bin:${PATH} ENV LD_LIBRARY_PATH${CUDA_HOME}/lib64:${LD_LIBRARY_PATH} WORKDIR /opt/ RUN yum install gzip tar gcc which xz zstd wget kmod findutils pciutils go git g cmake -y wget https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_570.86.10_linux.run mkdir /opt/tmp chmod 600 /opt/tmp bash cuda_12.8.0_570.86.10_linux.run -tmpdir /opt/tmp --silent --toolkit --no-man-page --no-drm --override wget https://developer.download.nvidia.cn/compute/cudnn/redist/cudnn/linux-x86_64/cudnn-linux-x86_64-9.12.0.46_cuda12-archive.tar.xz tar xf cudnn-linux-x86_64-9.12.0.46_cuda12-archive.tar.xz cp cudnn-linux-x86_64-9.12.0.46_cuda12-archive/include/cudnn*.h /usr/local/cuda-12.8/include/. cp cudnn-linux-x86_64-9.12.0.46_cuda12-archive/lib/libcudnn*.so* /usr/local/cuda-12.8/lib64/. git clone https://gitee.com/wangchaodong/ollama.git -b ${VERSION} cd /opt/ollama export GOPROXYhttps://goproxy.cn cmake --preset CUDA 12 cmake --build --parallel $(nproc) --preset CUDA 12 cmake --install build --component CUDA --strip mkdir -p /lib/ollama/ cp -rf dist/lib/ollama/* /lib/ollama/. cp -rf build/lib/ollama/* /lib/ollama/. go build -trimpath -ldflags -X github.com/ollama/ollama/version.Versionv0.17.7 -X github.com/ollama/ollama/server.moderelease -o /bin/ollama . yum remove wget go git g -y yum clean all rm -rf /opt/* EXPOSE 11434 ENV NVIDIA_DRIVER_CAPABILITIEScompute,utility ENV NVIDIA_VISIBLE_DEVICESall ENV OLLAMA_HOST 0.0.0.0 ENTRYPOINT [/bin/ollama] CMD [serve]四、生成ollama镜像docker build -f Dockerfile -t cr.delcare.cn/gpu/ollama:v0.17.7 .五、创建并运行ollama容器docker run -itd --name ollama --privileged --gpus all cr.delcare.cn/gpu/ollama:v0.17.7六、验证ollama服务是否正常运行1查看ipdocker inspect ollama|grep 172.172curl 172.17.0.4:114343查看日志启动时使用gpu