Change PowerInfer URL

README.md

@@ -81,7 +81,7 @@ Our evaluation is based on the framework lm-evaluation-harness and opencompass.
 
 ## Inference Speed Evaluation Results
 
-We utilize [PowerInfer](https://arxiv.org/pdf/2312.12456.pdf), a state-of-the-art acceleration framework leveraging activation sparsity.
+We utilize [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer), a state-of-the-art acceleration framework leveraging activation sparsity.
 Here we show the inference speed compared with llama.cpp/transformers.
 
 ## Limitation & Disclaimer