Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system

Alibaba Cloud claims to reduce Nvidia GPU used for serving unpopular models by 82% (emphasis mine)

> 17.7 per cent of GPUs allocated to serve only 1.35 per cent of requests in Alibaba Cloud’s marketplace, the researchers found

Instead of 1192 GPUs they now use 213 for serving those requests.

I’m slightly confuse as to how all this works. Do the GPUs just sit there with the models on them when the models are not in use?

I guess I’d assumed this sort of thing would be allocated dynamically. Of course, there’s a benefit to minimizing the number of times you load a model. But surely if a GPU+model is idle for more than a couple minutes it could be freed?

(I’m not an AI guy, though—actually I’m used to asking SLURM for new nodes with every run I do!)

Loading a model takes at least a few seconds, usually more, depending on model size, disk / network speed and a bunch of other factors.

If you're using an efficient inference engine like VLLM, you're adding compilation into the mix, and not all of that is fully cached yet.

If that kind of latency isn't acceptable to you, you have to keep the models loaded.

This (along with batching) is why large local models are a dumb and wasteful idea if you're not serving them at enterprise scale.

Can you elaborate the last statement? Don't quite understand why loading local LLM to GPU RAM, using it for the job and then "ejecting" is "dumb and wasteful" idea?