qwen-api / Dockerfile
Ngixdev's picture
Switch to Docker SDK with CUDA for llama-cpp
31b5080 verified
raw
history blame
526 Bytes
FROM nvidia/cuda:12.4.0-devel-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive
ENV CMAKE_ARGS="-DGGML_CUDA=on"
ENV FORCE_CMAKE=1
RUN apt-get update && apt-get install -y \
python3 \
python3-pip \
git \
cmake \
build-essential \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /app
RUN pip3 install --no-cache-dir --upgrade pip
RUN pip3 install --no-cache-dir llama-cpp-python
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt
COPY app.py .
EXPOSE 7860
CMD ["python3", "app.py"]