Dockerfile

FROM python:3.9-slim

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV TRANSFORMERS_CACHE=/app/cache
ENV HF_HOME=/app/cache
ENV PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.6,max_split_size_mb:128
# Optimize for multiple large models
ENV TRANSFORMERS_OFFLINE=0
ENV HF_HUB_ENABLE_HF_TRANSFER=1
ENV TOKENIZERS_PARALLELISM=false
# Reduce memory fragmentation
ENV MALLOC_TRIM_THRESHOLD_=100000

# Install system dependencies for better performance
RUN apt-get update && apt-get install -y \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH

# Set working directory
WORKDIR /app

# Copy requirements and install dependencies
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt && \
    pip install --no-cache-dir hf_transfer

# Copy application code
COPY --chown=user . .

# Create cache directory
RUN mkdir -p /app/cache

# Expose port
EXPOSE 7860

# Run the application
CMD ["python", "-u", "app.py"]