CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference
- Published
- Source
- arXiv
- Paper number
- 1110
- Field
- Machine Learning
- arXiv ID
- 2609.26300
Key points
- Compensation-aware KV cache selection accounting for pruned token contributions
- Accelerates inference with minimal degradation versus sparse attention
- Relieves long-context inference bottlenecks
- Applicable to cutting long-trajectory costs in agent harnesses
Paper links
External research summaries. These are not HDATF publications or measured product results.