Spaces:
Sleeping
Sleeping
File size: 1,462 Bytes
a36f560 6b859f2 2043365 a36f560 2043365 d174be4 dd29a6d d174be4 a36f560 7fff563 a36f560 55d10ea 2043365 d174be4 bd3417a 2043365 d174be4 d25a17f 2043365 d174be4 2043365 3a7a125 2043365 3a7a125 2043365 a36f560 d174be4 |
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 |
# Hugging Face Spaces compatible Dockerfile - V4 GPU INT4
FROM python:3.10-slim
# Set environment variables for V4 GPU deployment
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
PYTHONPATH=/app \
HOME=/tmp \
USER=user \
ENABLE_V1_WARMUP=false \
ENABLE_V2_WARMUP=false \
ENABLE_V4_WARMUP=true \
V4_MODEL_ID=Qwen/Qwen2.5-1.5B-Instruct \
V4_ENABLE_QUANTIZATION=true \
V4_USE_FP16_FOR_SPEED=true \
HF_HOME=/tmp/huggingface \
TRANSFORMERS_NO_TORCHAO=1 \
OMP_NUM_THREADS=1
# Set work directory
WORKDIR /app
# Install minimal system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
curl ca-certificates && rm -rf /var/lib/apt/lists/*
# Copy requirements first for better caching
COPY requirements.txt .
# Install Python dependencies
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir -r requirements.txt
# Copy application code
COPY app/ ./app/
COPY pytest.ini .
# Create cache directory for HuggingFace models
RUN mkdir -p /tmp/huggingface && chmod -R 777 /tmp/huggingface
# Expose port (Hugging Face Spaces uses port 7860)
EXPOSE 7860
# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=60s --retries=3 \
CMD curl -f http://localhost:7860/health || exit 1
# Simple startup - V4 model will download during warmup (with GPU INT4 quantization)
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
|