Comment by gitpusher42
4 hours ago
I double checked m2 logs. Cache hit rate is about 59-69%. 250-320MB went through `pread` per generated token. It is 3gb/s during this i/o phase.
4 hours ago
I double checked m2 logs. Cache hit rate is about 59-69%. 250-320MB went through `pread` per generated token. It is 3gb/s during this i/o phase.
No comments yet
Contribute on Hacker News ↗