Earlier quoted context omitted.
I want to know what a non-boring flight would be like
Snakes on a plane
Airforce One
Non-determinism in GPT-4 is caused by Sparse MoE
61–70 of 186 posts
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#62Not sure I understand the excerpt from the referenced paper. Is it saying that part of its more-efficient inferencing relies on mixing tokens from completely-separate inputs – eg, from other users? And then, depending on what other inputs chance into the same grouping, the relative assignment-to-'experts' varies, and thus the eventual completions? If so, I'd see that as not just introducing non-determinism, but also…
The results are showing essentially 12 unique responses from 30 tries… not what you would expect from mixing tokens.
I think it groups the batch up differently, so if I have a batch of 10, and it groups it up into 2 groups of 5, if my prompt makes it to the second group or 1st group I get a different answer. But if I’m in the same location in the batch, then I get the same answer.
The whole batch is deterministic given the same batch (sequences and ordering), but if you shuffle the batch then you lose that determinism.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#63Mixture of Experts
Thanks. I assumed it was Margin of Error. The article doesn't expand the acronym until midway through the post, where it appears almost accidentally. Perhaps the intended audience is a mixture of experts, of which I'm not a part.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#64Floating point inaccuracies are generally deterministic - running the same calculations twice ought to yield the same results, down to the bit.
You only get divergent results if there is some other source of state or entropy: not zeroing buffers correctly, race conditions, not setting rounding mode flags consistently, etc…
From the quality of the code I’ve seen being cobbled together in the AI/ML ecosystem I would assume all three of those issues going on, and maybe more.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#65I wonder if there’s a side channel attack in there waiting to happen..
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#66Earlier quoted context omitted.
It would be bad for single-consumer-GPU inference setups.
Not an expert (no pun intended), but MoE where each expert is actually just a LoRA adaptor on top of the base model gets me pretty excited. Since LoRA adaptors can be swapped in and out at runtime, it might be possible to get decent performance without a lot of extra memory pressure.
While MoE-LoRAs are exciting in themselves, they are a very different pitch from full on MoEs. If the idea behind MoEs is that you want completely separate layers to handle different parts of the input/computation, then it is unlikely that you can get away with low-rank tweaks to an existing linear layer.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#67Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.
Pick something you’re interested in and have a passing knowledge of.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#68How interesting. I was just discussing this last night with our analysts after I experimentally noticed that temp=0.0 (and all penalties/top_p set accordingly) still showed non-determinate behavior. Wasn't sure why this was, and now this article comes about.
The explanation makes quite a bit of sense.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#69Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.
> I noticed people from hacker news routinely read scientific papers. Do they? I suspect that most don't, and those that do are either in specialized careers or are engaged in some kind of scientific research. Some interesting research gets disseminated via Twitter and chatrooms. Or maybe you follow a podcast that mentions new research. But you might also be following new publications from a handful of reputable jour…
I strongly agree.
Once upon a time, I was in condensed matter physics. I was (and remain) interested in a very specific niche within that, and I read a small handful of the papers that were published each week. I’m not actively researching or publishing anymore so I cap this to one or two per month now, and mostly scan over them to see if anything piques my interest.
I was still interested in condensed matter as a whole, at the time, and attended group seminars once a month to see what other people were currently excited about - there wasn’t any hope of me reading a cross section of all condensed matter papers because there is far more published per week than I’d be physically able to even glimpse at, and most of it is stuff I don’t understand or particularly care about.
I was likewise interested in physics as a whole, and twice a year I’d attend a departmental seminar and see what people in the entire department were interested in. Most was far over my head, but it still directed me to a small handful of papers that I’d read for the hell of it. Of course, I couldn’t do this without first hearing people review the research. There’s far more published per day in physics as a whole than I could read in a year, and most of it I’d find unrelatable and uninteresting.
I guess where I’m going with this is that anyone with a specific interest is already reading papers. It’s their job. Anyone with a general interest would find actively pursing paper hunting to be a waste of time with a ridiculously bad signal to noise ratio. Instead, they should use channels that align closely with their own interests, through which they can get recommendations to read papers from the aforementioned specialists who have already filtered out much of the noise themselves. At that point, they should actually read the resulting papers.
There is another trick, though, and that’s to find an individual who publishes two unrelated pieces of work that you find interesting, then read their work and maybe those of their coauthors. Be careful, though, because this is a slippery slope to specialising, after which you’ll find yourself back at the point where you don’t aren’t following 99.9% of the stuff you wanted to follow in the first place.
Re: Non-determinism in GPT-4 is caused by Sparse MoE
#70Floating point inaccuracies are generally deterministic - running the same calculations twice ought to yield the same results, down to the bit. You only get divergent results if there is some other source of state or entropy: not zeroing buffers correctly, race conditions, not setting rounding mode flags consistently, etc… From the quality of the code I’ve seen being cobbled together in the AI/ML ecosystem I would as…
No, this is not true for GPUs. https://www.twosigma.com/articles/a-workaround-for-non-deter...
(In this particular case, the order in which the numbers are summed up is non-deterministic due to GPU parallelism, which may change the result slightly.)
I would generally refrain from insulting other people's code if you don't know much about the system it's written on.
.
Editing here since all the replies to this are mostly saying the same thing: Yes, CPUs can also be parallel and it can happen there as well, but unlike a CPU where most instructions on their own are deterministic, CUDA provides primitives that aren't. This is very much by design (as they're faster than their deterministic counterparts), and I mostly just take issue with how parent phrased this as a bug caused by bad code.