I’ve been working on robotics for a few months now. I have built an arm, started receiving parts for my quadruped, and have learned enough RL to at least hold opinions on it (my background is ML/LLM training, so a bit different).
Eventual goal before I return to work next year is to have a robot I can take on walks with me that will pick up trash.
It’s a mobile platform, so saving 100 w on the CPU would make a difference. That’s the answer I tell myself, the real answer is because it would look hilarious :D
What’s the bottleneck? Once I’ve got the model and data onto the GPU my only cost is launching CUDA kernels right?
Not sure if that blog post is relevant, but even if it is it shows a 3060 gets //way// faster throughout than the igpu it is testing. I suppose I can test this myself by plugging my 3070 into the NVME on my desktop.
Does anyone have experience of putting a huge GPU on something like this and using it for inference? You'd be limited by data feeding over the NVME port, but otherwise you won't be bottlenecked right? Seems like a light weight and cute way to limit non-inference power/weight without having to pay the price of a Jetson board.