abetlen / abetlen/llama-cpp-python

Smaller docker image CUDA example

未關閉
#1,119 1 則留言 0 個 reaction 已指派 0 人 在 GitHub 檢視
question
主要語言
Python
星號
10.6k
分支
1.4k
PR 合併指標
PR 指標待擷取

描述

ive been struggling some with a Cuda dockerfile sinze the devel image was so large the build ended up at almost 8gb, i came up with this. just wanted to share it:
```

FROM nvidia/cuda:12.1.1-devel-ubuntu22.04 AS builder

RUN apt-get update && apt-get upgrade -y \
&& apt-get install -y git build-essential \
python3 python3-pip gcc wget \
ocl-icd-opencl-dev opencl-headers clinfo \
libclblast-dev libopenblas-dev \
&& mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd

# setting build related env vars
ENV CUDA_DOCKER_ARCH=all
ENV LLAMA_CUBLAS=1

# Install depencencies
RUN python3 -m pip install --user --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context

# Install llama-cpp-python (build with cuda)
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install --user llama-cpp-python

FROM nvidia/cuda:12.1.1-runtime-ubuntu22.04

RUN apt-get update && apt-get upgrade -y \
&& apt-get install -y git build-essential \
python3 python3-pip gcc wget \
ocl-icd-opencl-dev opencl-headers clinfo \
libclblast-dev libopenblas-dev \
&& mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd

# Copy libraries from build local path
COPY --from=builder /root/.local /root/.local
COPY --from=builder /tmp/*.txt /tmp/
ENV PATH=/root/.local:$PATH

```

the final image ended up att aroung 2gb and GPU support is working as expected..

貢獻指南

開啟貢獻指南

評估

這個 Issue 還沒有評估資料。

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。