2 papers
cs.AR2025
MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
Huizheng Wang, Zichuan Wang, Zhiheng Yue +8
Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. Thi…
cs.CR2025
EFFACT: A Highly Efficient Full-Stack FHE Acceleration Platform
Yi Huang, Xinsheng Gong, Xiangyu Kong +8
Fully Homomorphic Encryption (FHE) is a set of powerful cryptographic schemes that allows computation to be performed directly on encrypted data with an unlimited depth. Despite FH…