ThinK
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
proposes an approach to address inefficiencies in KV cache memory consumption; it focuses on the long-context scenarios and the inference side of things; it presents a query-dependent KV cache pruning method to minimize attention weight loss while selectively pruning the least significant channels
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack