Jialong Han
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.
GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.
Papers
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
Junjie Peng, You Wu, Haoyi Wu, Jialong Han +3 more
GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.