Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

If the explanation really is, as many comments here suggest, that prompts can be run in parallel in batches at low marginal additional cost, then that feels like bad news for the democratization and/or local running of LLMs. If it’s only cost-effective to run a model for ~thousands of people at the same time, it’s never going to be cost-effective to run on your own.

You can knock off a zero or two just by time shifting the 700 million distinct users across a day/week and account for the mere minutes of compute time they will actually use in each interaction. So they might no see peaks higher than 10 million active inference session at the same time.

Conversely, you can't do the same thing as a self hosted user, you can't really bank your idle compute for a week and consume it all in a single serving, hence the much more expensive local hardware to reach the peak generation rate you need.

I think this article can be interesting:

https://www.seangoedecke.com/inference-batching-and-deepseek...

Here is an example of what happens

> The only way to do fast inference here is to pipeline those layers by having one GPU handle the first ten layers, another handle the next ten, and so on. Otherwise you just won’t be able to fit all the weights in a single GPU’s memory, so you’ll spend a ton of time swapping weights in and out of memory and it’ll end up being really slow. During inference, each token (typically in a “micro batch” of a few tens of tokens each) passes sequentially through that pipeline of GPUs

First off I’d say you can run models locally at good speed, llama3.1:8b runs fine a MacBook Air M2 with 16GB RAM and much better on a Nvidia RTX3050 which are fairly affordable.

For OpenAI, I’d assume that a GPU is dedicated to your task from the point you press enter to the point it finishes writing. I would think most of the 700 million barely use ChatGPT and a small proportion use it a lot and likely would need to pay due to the limits. Most of the time you have the website/app open I’d think you are either reading what it has written, writing something or it’s just open in the background, so ChatGPT isn’t doing anything in that time. If we assume 20 queries a week taking 25 seconds each. That’s 8.33 minutes a week. That would mean a single GPU could serve up to 1209 users, meaning for 700 million users you’d need at least 578,703 GPUs. Sam Altman has said OpenAI is due to have over a million GPUs by the end of year.

I’ve found that the inference speed on newer GPUs is barely faster than older ones (perhaps it’s memory speed limited?). They could be using older clusters of V100, A100 or even H100 GPUs for inference if they can get the model to fit or multiple GPUs if it doesn’t fit. A100s were available in 40GB and 80GB versions.

I would think they use a queuing system to allocate your message to a GPU. Slurm is widely used in HPC compute clusters, so might use that, though likely they have rolled their own system for inference.

The idea that a GPU is dedicated to a single inference task is just generally incorrect. Inputs are batched, and it’s not a single GPU handling a single request, it’s a handful of GPUs in various parallelism schemes processing a batch of requests at once. There’s a latency vs throughput trade off that operators make. The larger that batch size the greater the latency, but it improves overall cluster throughput.