The authors first isolate the source of quality loss in position-independent caching (PIC) by conducting controlled experiments.
Query-side adapters recover full-context quality in KV cache reuse
Attuner inserts lightweight adapters into query projections to read frozen artifact caches, matching prefill quality with up to 3.73x speedup.
Chinese Tech
Xinghao Chen · Junnan Dong · Cai Ke · Chak Tou Leong · Haocheng Sun · Keyu Chen · +5 more
Eastern Institute of Technology, Ningbo · The Hong Kong Polytechnic University · Tencent Youtu Lab
Research Digest··3 min read
The authors propose Attuner, a method that learns to read frozen key-value (KV) caches of reusable content artifacts via query-side adaptation, eliminating the need for cache recomputation.
Why this paper
From Tencent Youtu Lab and 2 others · Part of Context Engineering for Agents, now 38 papers
In one line
Query-side adaptation of attention projections enables KV cache reuse that matches full prefill quality without recomputation, achieving up to 3.73x speedup.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§