Re:Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-G...
by spwa4 on Monday February 23, 2026 @02:40AM
(#47119246)
I've found this to often be untrue when optimizing on the CPU. I wish someone would pay me to dive deep into this problem and the scheduling problem. I'd be amazed if I can't squeeze out a 50% speed increase on both problems.
[ Parent
| on HN ]
There are no comments on this comment yet.