Dockerfile

FROM nvidia/cuda:12.5.1-cudnn-devel-ubuntu20.04

ENV DEBIAN_FRONTEND=noninteractive \
    TZ=Asia/Kolkata

# Remove any third-party apt sources to avoid issues with expiring keys.
RUN rm -f /etc/apt/sources.list.d/*.list && \
    apt-get update && apt-get install -y --no-install-recommends \
    curl \
    ca-certificates \
    sudo \
    git \
    wget \
    procps \
    git-lfs \
    zip \
    unzip \
    htop \
    vim \
    nano \
    bzip2 \
    libx11-6 \
    build-essential \
    libsndfile-dev \
    software-properties-common \
 && rm -rf /var/lib/apt/lists/*

RUN add-apt-repository ppa:flexiondotorg/nvtop && \
    apt-get upgrade -y && \
    apt-get install -y --no-install-recommends nvtop

RUN curl -sL https://deb.nodesource.com/setup_21.x  | bash - && \
    apt-get install -y nodejs && \
    npm install -g configurable-http-proxy

# Create a working directory
WORKDIR /app

# Create non-root user
RUN adduser --disabled-password --gecos '' --shell /bin/bash user \
 && chown -R user:user /app
RUN echo "user ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/90-user
USER user

ENV HOME=/home/user
RUN mkdir $HOME/.cache $HOME/.config \
 && chmod -R 777 $HOME

# Install Miniconda
ENV CONDA_AUTO_UPDATE_CONDA=false \
    PATH=$HOME/miniconda/bin:$PATH
RUN curl -sLo ~/miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-py39_4.10.3-Linux-x86_64.sh \
 && chmod +x ~/miniconda.sh \
 && ~/miniconda.sh -b -p ~/miniconda \
 && rm ~/miniconda.sh \
 && conda clean -ya

WORKDIR $HOME/app

#######################################
# Root section
#######################################
USER root

# Optional extra packages
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3-dev python3-pip python3-venv \
 && rm -rf /var/lib/apt/lists/*

RUN mkdir /data && chown user:user /data

#######################################
# End root section
#######################################
USER user

# Install Python requirements for vLLM
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir vllm

# Download model at build time (optional)
RUN python3 -m vllm.entrypoints.api_server --model unsloth/llama-2-7b-bnb-4bit --download-only

# Copy source code
COPY --chown=user . $HOME/app

RUN chmod +x start_server.sh

# Set env for vLLM
ENV PYTHONUNBUFFERED=1 \
    VLLM_HOST=0.0.0.0 \
    VLLM_PORT=7860

# Expose port
EXPOSE 7860

# Start vLLM API server
CMD ["python3", "-m", "vllm.entrypoints.api_server", "--model", "unsloth/llama-2-7b-bnb-4bit", "--host", "0.0.0.0", "--port", "7860"]