undefined | Better HN

0 pointsDylan168074mo ago0 comments

Depends on what you're doing. I'm pretty sure the bandwidth for inference isn't much.

0 comments

Depends, if it's tensor parallel or pipeline parallel. Only PP doesn't pass too much. TP does

j / k navigate · click thread line to collapse

0 pointsDylan168074mo ago0 comments

Depends on what you're doing. I'm pretty sure the bandwidth for inference isn't much.

Depends, if it's tensor parallel or pipeline parallel. Only PP doesn't pass too much. TP does

j / k navigate · click thread line to collapse