
Attention-aware KV cache placement extends SSD lifetime without sacrificing cache hit rate
The authors propose Gandalf, a KV cache offloading system for LLM serving that uses attention layer type as a placement signal when deciding which caches to write to SSD. By preferentially admitting full-attention KV caches over linear- and sparse-attention states, Gandalf extends SSD lifetime by 7.3x on average without measurably reducing cache hit rate.



































