Speaker unverified: uncertainty

Transcript context

…Yeah, there's a lot of really good info there. One thing I'll just briefly touch on for quantization. There was a recent Noam Shazir blog post. Noam is writing again for some reason, and he was talking about native FP8 training. It seems like that is most useful for inference. That is what you expect the open source community to do with your weights once you release them anyway. Is there any movement or thinking about just moving to FP8 or whatever other new format is in vogue these days? Also, these papers like to train like some, I forget the name, but like there's two follow papers on like just a zero one or minus one weights. And like, there's a lot of work there. I think it's promising directions of all regarding FP8 in particular, those are the possibility for the community to try FP8 or other methods that are very easy at fine tuning time. So I'm really looking forward to what the community can do there. Overall, like scaling, I don't know if it's all you need, but I will not bet against scaling. And one of the ways to get more scale is by having better algorithms that we can train for the same level for less compute. Less compute and less memory. Yeah, like inference time memory is becoming a real constraint.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.