🛰️ Daily AI Frontier
‹ back to 2026-07-28

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding

Research Efficiency & Systems

Merged summary

TL;DR - LOCKS accelerates long-context LLM decoding by using compact, page-local spectral summaries to select which KV-cache pages deserve attention. It matches FullKV aggregate quality at 100K+ context while attending to about 2% of tokens and halves per-token latency at 1M tokens.

  • Each KV-cache page gets a compact summary roughly one-tenth its size, preserving page-specific attention directions.
  • Page selection reads summaries rather than candidate keys or values, then applies attention only to the highest-mass pages.
  • LOCKS outperforms baseline selectors on retrieval-dense and long-form reasoning benchmarks, where shared-basis approaches can degrade sharply.
  • It integrates with unmodified vLLM as a drop-in plugin and supports batched decoding with full CUDA graphs.

Sources (1)

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding

arXiv cs.LG Junsung Hwang 2026-07-27 arXiv:2607.24555

TL;DR - LOCKS accelerates long-context LLM decoding by using compact, page-local spectral summaries to select which KV-cache pages deserve attention. It matches FullKV aggregate quality at 100K+ context while attending to about 2% of tokens and halves per-token latency at 1M tokens.

  • Each KV-cache page gets a compact summary roughly one-tenth its size, preserving page-specific attention directions.
  • Page selection reads summaries rather than candidate keys or values, then applies attention only to the highest-mass pages.
  • LOCKS outperforms baseline selectors on retrieval-dense and long-form reasoning benchmarks, where shared-basis approaches can degrade sharply.
  • It integrates with unmodified vLLM as a drop-in plugin and supports batched decoding with full CUDA graphs.
item →