Schedulable KV-Cache Eviction with a Probabilistic Sizing Bound for Real-Time LLM Decoding
Published in Targeting IEEE RTSS 2026, 2026
Manuscript and artifact in progress. Project artifact: SEER.
Recommended citation: Ziqing Li, "Schedulable KV-Cache Eviction with a Probabilistic Sizing Bound for Real-Time LLM Decoding." Targeting IEEE RTSS 2026.