by Ning-Chi Huang Papers
2 papers found
Conference
Palu: KV-Cache Compression with Low-Rank Projection
Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin et al.
ICLR 2025
18
citations
Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
Pei-Shuo Wang, Jian-Jia Chen, Chun-Che Yang et al.
NEURIPS 2025arXiv:2509.18344