ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression.
Saved in:
| Title: | ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression. |
|---|---|
| Authors: | Liu, Guangda1, Li, Chengwei1, Zhao, Jieru1, zhao-jieru@sjtu.edu.cn, Zhang, Chenqi1, Guo, Minyi1 |
| Source: | DAC: Annual ACM/IEEE Design Automation Conference; 2025, Issue 62, p1-7, 7p |
| Database: | Applied Science & Technology Source |
Be the first to leave a comment!
