People should check out Google's JAX. Work in a high level language and run anywhere. Nvidia should just be commodity hardware if people avoid vendor lock in.
Shimming CUDA is a waste of effort that only reinforces Nvidia's market dominance. Targeting higher level interfaces, Jax, Taichi, ArrayFire, etc is imho a better strategy. We have already seen systems like LLama.cpp and their ilk support alternative backends for training and inference.
Now the vast majority of the compute cycles have centered around a handful of model architectures, implementing those specific architectures in whatever bespoke hardware isn't difficult.
Target specific applications not the whole complex library/language layer.
nerpderp82|2 years ago
Now the vast majority of the compute cycles have centered around a handful of model architectures, implementing those specific architectures in whatever bespoke hardware isn't difficult.
Target specific applications not the whole complex library/language layer.
fisf|2 years ago
Somebody has to build those optimized backends -- it's not just a matter of people picking the wrong stack.
nerpderp82|2 years ago