作者位次 #5/5ACL 2026Poster· Natural Language Processing
The Pitfalls of KV Cache Compression
Alex Chen · Renato Geh · Aditya Grover · Guy Van den Broeck · Daniel Mingyi Israel
摘要
KV cache compression promises increased throughput and efficiency with negligible loss in performance. While the gains in throughput are indisputable and recent literature has indeed shown minimal degradation on particular benchmarks, in general the consequences of compression in realistic scenar...