Qiao Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1Architecture×1
Frequent co-authors
Research Timeline
2026
GPU Acceleration of TFHE-Based High-Precision Nonlinear Layers for Encrypted LLM Inference
The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.ARRecentApr 6, 2026
GPU Acceleration of TFHE-Based High-Precision Nonlinear Layers for Encrypted LLM Inference
Guoci Chen, Xiurui Pan, Qiao Li, Bo Mao +4 more
The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.
View →