HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by sprobertson | Hacker News Reader
Parent
Full thread
sprobertson
·
Wouldn't caching be in favor of lowest possible latency?
View on HN
Kubuxu
·
It might be faster to burn the compute instead of having to fetch the KV-cache over the network from an SSD.
Reply on news.ycombinator.com