Dockerfile

# ---------- BASE IMAGE ----------
FROM nvidia/cuda:12.2.0-devel-ubuntu22.04 AS base

# Set workdir inside container
WORKDIR /app

# Prevent interactive prompts
ENV DEBIAN_FRONTEND=noninteractive

# ---------- INSTALL DEPENDENCIES ----------
RUN apt-get update && apt-get install -y --no-install-recommends \
    git \
    build-essential \
    python3-pip \
    python3-dev \
    python3-venv \
    ffmpeg \
    libgl1 \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# ---------- COPY & INSTALL PYTHON DEPENDENCIES ----------
COPY requirements.txt .

RUN pip install --upgrade pip \
    && pip install --no-cache-dir -r requirements.txt

# ---------- COPY APP CODE ----------
COPY . .

# ---------- ENVIRONMENT VARIABLES ----------
ENV HF_HOME=/tmp/huggingface
ENV HF_HUB_CACHE=/tmp/huggingface/hub
ENV TRANSFORMERS_CACHE=/tmp/huggingface/transformers

ENV NVIDIA_VISIBLE_DEVICES=all
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

# ---------- EXPOSE PORT ----------
EXPOSE 7860

# ---------- START APP ----------
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]