Update Dockerfile

Dockerfile

@@ -1,30 +1,32 @@
-# Use a standard base image with CUDA support
-FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
+# 1. Start from the official NVIDIA CUDA development image. This is the key change.
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
 
-# Set environment variables for caching AND for CUDA libraries
+# 2. Set up the environment to be non-interactive and add Python paths
 ENV DEBIAN_FRONTEND=noninteractive
-ENV HF_HOME="/data/huggingface"
-ENV UV_CACHE_DIR="/data/uv_cache"
+ENV PATH="/root/.local/bin:${PATH}"
 
-# --- THE CRITICAL FIX ---
-# Tell the dynamic linker where to find the NVIDIA CUDA libraries.
-# This makes `libcuda.so.1` visible to vLLM.
-ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:$LD_LIBRARY_PATH
+# 3. Install Python 3.11, pip, and other essential tools
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3.11 \
+    python3-pip \
+    python-is-python3 \
+    git \
+    && rm -rf /var/lib/apt/lists/*
 
-# Install git and uv (for faster package installation)
-RUN apt-get update && apt-get install -y --no-install-recommends git && rm -rf /var/lib/apt/lists/*
+# 4. Install uv for fast package installation
 RUN pip install uv
 
-# Copy requirements and install them efficiently into the system environment
+# 5. Copy requirements and install them.
+# The base image is clean, so we need to install everything, including torch.
 COPY requirements.txt .
 RUN uv pip install --no-cache --system -r requirements.txt
 
-# Copy the application code into the container
+# 6. Copy the application code
 COPY ./app.py /app/app.py
 WORKDIR /app
 
-# Expose the port the app will run on
+# 7. Expose the port
 EXPOSE 7860
 
-# The command to run the FastAPI app
+# 8. Run the application with uvicorn
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]