alt Hacker NewsYes, 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.
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.