Create monorepo from known-good production state

bgbye/Dockerfile.gpu

@@ -0,0 +1,63 @@
+FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1
+
+# System deps (incl. GL + X libs so OpenCV works headless)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3 python3-venv python3-pip wget ca-certificates \
+    libgl1 libglib2.0-0 libsm6 libxext6 libxrender1 && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Upgrade pip first
+RUN python3 -m pip install --upgrade pip
+
+# Core Python deps
+RUN python3 -m pip install --no-cache-dir \
+      onnxruntime-gpu==1.22.0 \
+      rembg==2.0.67 \
+      fastapi==0.116.1 \
+      uvicorn[standard]==0.35.0 \
+      pillow==11.3.0 \
+      numpy==2.2.6 \
+      pydantic==2.11.7 \
+      opencv-python-headless==4.12.0.88
+
+# PyTorch CUDA 12.4
+RUN python3 -m pip install --no-cache-dir \
+      --index-url https://download.pytorch.org/whl/cu124 \
+      torch==2.4.1 \
+      torchvision==0.19.1
+
+# ML + HuggingFace stack (pinned to avoid BRIA RMBG compatibility bug)
+RUN python3 -m pip install --no-cache-dir \
+      transparent-background \
+      carvekit \
+      timm \
+      transformers==4.44.2 \
+      tokenizers==0.19.1 \
+      huggingface-hub==0.36.2 \
+      accelerate
+
+# Your server code
+COPY server /app/server
+
+# Remove sudo usage if present (containers already run as root)
+RUN if [ -f /app/server/setup.sh ]; then \
+      sed -i 's/^[[:space:]]*sudo[[:space:]]\+//g' /app/server/setup.sh; \
+    fi
+
+# Make sure scripts are executable
+RUN chmod +x /app/server/setup.sh /app/server/run.sh || true
+
+EXPOSE 7001
+
+# Healthcheck
+HEALTHCHECK --interval=30s --timeout=5s --retries=5 \
+  CMD wget -qO- http://localhost:7001/health || exit 1
+
+# Run API
+CMD ["bash", "/app/server/run.sh"]