Re:Apple M3 Ultra
by Der_Einzige on Wednesday March 05, 2025 @01:33PM
(#43270418)
No one who is using this for home use cares about anything except batch size 1 sequence size 1.
[ Parent
| on HN ]
What if you're doing bulk inference? The efficiency and throughput of bs=1 s=1 is truly abysmal.