Tree: Refactor code organization

Move common functions into their own folder and refactor the backends
to use their own folder as well.

Also cleanup imports and alphabetize import statments themselves.

Finally, move colab and docker into their own folders as well.

Signed-off-by: kingbri <bdashore3@proton.me>

docker/.dockerignore

@@ -0,0 +1 @@
+models/

docker/Dockerfile

@@ -0,0 +1,30 @@
+# 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/*
+
+# Set the working directory in the container
+WORKDIR /usr/src/app
+
+# Get requirements
+COPY requirements.txt requirements.txt
+
+# Install torch with CUDA support and exllamav2
+RUN pip install torch --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 current directory contents into the container at /usr/src/app
+COPY . .
+
+# Make port 5000 available to the world outside this container
+EXPOSE 5000
+
+# Run main.py when the container launches
+CMD ["python3", "main.py"]

docker/docker-compose.yml

@@ -0,0 +1,20 @@
+version: '3.8'
+services:
+  tabbyapi:
+    build:
+      context: ..
+      dockerfile: ./docker/Dockerfile
+    ports:
+      - "5000:5000"
+    environment:
+      - NAME=TabbyAPI
+      - NVIDIA_VISIBLE_DEVICES=all
+    volumes:
+      - ./models:/usr/src/app/models
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]