ninja  # For faster builds.
psutil
ray >= 2.9
sentencepiece  # Required for LLaMA tokenizer.
numpy
torch == 2.1.2
transformers >= 4.37.0 # Required for Qwen2
xformers == 0.0.23.post1  # Required for CUDA 12.1.
fastapi
uvicorn[standard]
pydantic >= 2.0  # Required for OpenAI server.
aioprometheus[starlette]
pynvml == 11.5.0