alt
Hacker News
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
5 points
•
by
gmays
•
last Sunday at 4:02 AM
•
1 comment
•
view on HN
Comments
ricardobeat
•
today at 10:50 AM
The abstract reads like slop. Authors working on LLMs should know better than that.
The abstract reads like slop. Authors working on LLMs should know better than that.