LLM TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices Paper โข 2410.00531 โข Published 8 days ago โข 28
TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices Paper โข 2410.00531 โข Published 8 days ago โข 28