Translated Data: The IPADS Lab at Shanghai Jiao Tong University has released the PowerInfer framework, which boosts inference speed by 11 times for models with 80GA100 activity without the need for quantization. Utilizing FP16 precision, it addresses the bottleneck of running large models on personal computers. PowerInfer has been met with great enthusiasm, offering a new solution for the application of large models on consumer-grade hardware.