Tsinghua open-sources AKV cache server for LLM agents on SGLang
The available page text is a cookie notice, so release details, benchmarks and license terms are not stated.
28
- Mentions · 7d1
- Mentions · 30d3
- All mentions3
- First seenOct 19, 2026
- Last mentioned5d ago
Timeline
3 articles · newest firstPaper proposes cache engineering so agents edit KV cache in place
A rolling-drop policy raised benchmark scores 1.7 points and cut cost 27.7% versus summarization.
42
AKV lets agents drop and reposition KV cache without re-prefill
A rolling-drop policy raises benchmark scores 1.7 points and cuts average cost 27.7% versus summarization.
52
Appears with
- SGLangproduct · 1
- Tsinghua AIorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.