KV-cache hit rate

termopen source

The share of prompt tokens served from the model's key-value cache; higher means lower latency and cost.

Signals

No signals collected yet.

How it stacks up

KV-cache hit rate next to similar tools, using only numbers both have. Bigger isn't always better: read each number's meaning first.

No fair match yet: no similar tool shares at least two of KV-cache hit rate's numbers. We only compare like-for-like numbers.

Relationship map

No mapped relationships yet