Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets

Published
Source
arXiv
Paper number
1114
Field
Machine Learning
arXiv ID
2609.27981

Key points

  • Reformulates KV-cache eviction as a risk-control problem
  • Guarantees no individual request suffers material quality degradation
  • Addresses worst-case performance that average metrics miss
  • Stability foundation for production LLM deployment

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)