Irminsul recovers up to 83% of prompt tokens above exact-prefix matching and delivers 63% prefill energy savings per cache hit on MLA-MoE models by content-hashing CDC chunks and applying closed-form kr correction.
How attention sinks emerge in large language models: An interpretability perspective
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving
Irminsul recovers up to 83% of prompt tokens above exact-prefix matching and delivers 63% prefill energy savings per cache hit on MLA-MoE models by content-hashing CDC chunks and applying closed-form kr correction.