Not really, for GPU computation, PyTorch, TensorFlow or JAX are the baselines (t... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		albertzeyer on Oct 4, 2023 \| parent \| context \| favorite \| on: MatX: Efficient C++17 GPU numerical computing libr... Not really, for GPU computation, PyTorch, TensorFlow or JAX are the baselines (they are not just for ML stuff). Even for CPU, that's a more relevant comparison.

KeplerBoy on Oct 4, 2023 [–]

I agree in principle, but my experience is that researchers writing code just default to NumPy.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact