Model Serving · Data artifact
FIFO KV Cache Eviction Policy
Data artifactModel ServingModelsarc:FIFOKVCacheEvictionPolicy
An eviction policy that removes the oldest requests' KV caches first.
Responsibility. Evicts the oldest KV caches first.
Variant of KV Cache Eviction Policy abstract
When to choose. Choose when all requests have similar priority.
Relationships
alternative to variability
Sources
- Ch4.4: T. Nguyen, "Performance Profiling and Optimization," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.4. ISBN: 9798244538229.