HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by p_stuart82 | Hacker News Reader
Full thread
p_stuart82
·
Does this catch intermittent fallback between requests?
View on HN
logickkk1
·
Yes, picchio monitors a running llama-server on a timer and flags when the prefill/decode ratio goes CPU-shaped. I hot-swapped one mid-run. probe 4 caught ENGAGED -> NOT ENGAGED.
Reply on news.ycombinator.com