chari / requirements.txt
danielramos
feat: hybrid engine with real CUDA GPU acceleration and streaming on Hugging Face ZeroGPU
bf59288
Raw History Blame Contribute Delete
238 Bytes
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
llama-cpp-python>=0.3.0
fastapi>=0.115.0
uvicorn[standard]>=0.30.0
langgraph>=0.2.0
langchain-core>=0.3.0
huggingface_hub
gradio
transformers>=4.44.0
accelerate>=0.33.0