llama-3.2-1B-FastApi / requirements.txt
parth parekh
added more speed
9e1ad54
raw
history blame
232 Bytes
fastapi
transformers
torch
uvicorn
python-dotenv
optimum[onnxruntime] # For CPU optimizations with ONNX Runtime
accelerate # For managing multi-device setup (CPU/GPU)
gunicorn # For running multiple workers