requirements.txt

# Core dependencies
fastapi==0.109.2
uvicorn==0.27.1
pydantic==2.6.1
huggingface_hub
bitsandbytes
# For API requests and handling
requests==2.31.0
python-multipart==0.0.9

# For model handling
torch==2.3.1
transformers==4.43.1
vllm==0.5.3.post1
accelerate==0.27.2

# Optional but recommended for performance
python-jose==3.3.0  # for JWT handling if you add auth later
gunicorn==21.2.0    # for production deployment
python-dotenv==1.0.0  # for environment variables
ctransformers
pyllamacpp==2.4.0