Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity

Name: Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
Duration: 15 min
Description: Talk from IEEE Symposium on Security and Privacy 2025.

Guang Yan, Yuhui Zhang, Zimu Guo, Lutan Zhao, Xiaojun Chen, Chen Wang

IEEE Symposium on Security and Privacy 2025 · Day 2 · Secure Data Processing II