Re:An analysis of DeepSeek's R1-Zero and R1
by coder543 on Wednesday January 29, 2025 @06:38PM
(#42872825)
Sure, but that default batch size would only matter if the person in question was actually generating and measuring parallel requests, not just measuring the straight line performance of sequential requests... and I have no confidence they were.
[ Parent
| on HN ]
There are no comments on this comment yet.