LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.
A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.
