加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
Dockerfile 1.15 KB
一键复制 编辑 原始数据 按行查看 历史
discus0434 提交于 2023-12-21 11:05 . add Dockerfile
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1 \
CUDA_HOME=/usr/local/cuda-11.8 TORCH_CUDA_ARCH_LIST="8.6"
RUN rm /bin/sh && ln -s /bin/bash /bin/sh
RUN apt-get update && apt-get install -y --no-install-recommends \
make \
wget \
tar \
build-essential \
libgl1-mesa-dev \
curl \
unzip \
git \
python3-dev \
python3-pip \
libglib2.0-0 \
&& apt clean && rm -rf /var/lib/apt/lists/* \
&& ln -s /usr/bin/python3 /usr/bin/python
RUN echo "export PATH=/usr/local/cuda/bin:$PATH" >> /etc/bash.bashrc \
&& echo "export LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH" >> /etc/bash.bashrc \
&& echo "export CUDA_HOME=/usr/local/cuda-11.8" >> /etc/bash.bashrc
RUN pip3 install \
torch==2.1.0 \
torchvision==0.16.0 \
xformers \
--index-url https://download.pytorch.org/whl/cu118
COPY . /streamdiffusion
WORKDIR /streamdiffusion
RUN python setup.py develop easy_install streamdiffusion[tensorrt] \
&& python -m streamdiffusion.tools.install-tensorrt
WORKDIR /home/ubuntu/streamdiffusion
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化