New KV cache compaction technique cuts LLM memory 50x without accuracy loss

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — ...
Business Wire

Development of Cache Random Function to Enable Fast and Secure Data Access Between CPU Memories

TOKYO--(BUSINESS WIRE)--NTT Corporation (NTT) in collaboration with the Research Institute of Electrical Communication, Tohoku University and CASA (Cyber Security in the Age of Large-Scale Adversaries ...
Security

NTT advances CPU security with new cache random function

Tokyo – August 16, 2023 – NTT Corporation (NTT) in collaboration with the Research Institute of Electrical Communication, Tohoku University and CASA (Cyber Security in the Age of Large-Scale ...