Add basic docker support

Docker

@@ -0,0 +1,37 @@
+# Use an official CUDA runtime with Ubuntu as a parent image
+FROM nvidia/cuda:12.2.0-devel-ubuntu22.04
+
+# Install Python and pip
+RUN apt-get update && apt-get install -y \
+    python3.11 \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Alias python and pip to python3 and pip3
+#RUN ln -s /usr/bin/python3 /usr/bin/python
+
+# Set the working directory in the container
+WORKDIR /usr/src/app
+
+# Copy the current directory contents into the container at /usr/src/app
+COPY . .
+
+# Install torch with CUDA support and exllamav2
+RUN pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121
+RUN pip install exllamav2
+
+# Install any other needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the sample config file to the main config
+RUN cp config_sample.yml config.yml
+
+# Make port 5000 available to the world outside this container
+EXPOSE 5000
+
+# Define environment variable
+ENV NAME World
+
+# Run main.py when the container launches
+CMD ["python3", "main.py"]
+

docker-compose.yml

@@ -0,0 +1,13 @@
+version: '3.8'
+services:
+  tabbyapi:
+    build: .
+    ports:
+      - "5000:5000"
+    runtime: nvidia
+    environment:
+      - NAME=TabbyAPI
+      - NVIDIA_VISIBLE_DEVICES=all
+#    volumes:
+#      - /path/to/models:/usr/src/app/models
+#      - /path/to/config:/usr/src/app/config.yml