Spaces:
Sleeping
Sleeping
File size: 1,583 Bytes
5503fad 0f7413f 9d309ad 5503fad 9d309ad 0f7413f 9d309ad 5503fad 9d309ad 5503fad 9d309ad 0f7413f 9d309ad b105c47 9d309ad b105c47 9d309ad b105c47 9d309ad b105c47 9d309ad 5503fad 9d309ad 5503fad b105c47 9d309ad 0f7413f 5503fad |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
# Use NVIDIA CUDA base image with Python support (ONLY for GPU Spaces)
FROM nvidia/cuda:12.1.1-runtime-ubuntu22.04
# Set working directory
WORKDIR /app
# Install Python and system dependencies
RUN apt-get update && apt-get install -y \
python3.10 \
python3-pip \
python3.10-venv \
python3.10-dev \
build-essential \
cmake \
git \
curl \
wget \
&& rm -rf /var/lib/apt/lists/*
# Make python3.10 the default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1
RUN update-alternatives --install /usr/bin/pip pip /usr/bin/pip3 1
# Upgrade pip
RUN pip install --upgrade pip
# Install prebuilt llama-cpp-python CUDA wheel
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install --no-cache-dir llama-cpp-python==0.2.90 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121
# Copy requirements.txt and install remaining dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# Create a non-root user
RUN useradd -m -u 1000 user
# Create cache directory with proper permissions
RUN mkdir -p /app/.cache/huggingface
RUN chown -R user:user /app
# Copy app code
COPY . .
RUN chown -R user:user /app
# Create models directory
RUN mkdir -p models && chown -R user:user models
# Switch to non-root user
USER user
# Environment variables
ENV GRADIO_SERVER_NAME="0.0.0.0"
ENV GRADIO_SERVER_PORT=7860
ENV CUDA_VISIBLE_DEVICES=0
ENV HF_HOME=/app/.cache/huggingface
ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
# Expose Gradio port
EXPOSE 7860
# Start app
CMD ["python", "app.py"] |