Evals in 2025: going beyond simple benchmarks to build models people can usegithub.com·80 pts·jxmorris12·8
Sequence Parallelism: Long Sequence Training from System Perspective (2021)arxiv.org·2 pts·jxmorris12·0
The scientific method and its application to the science of deep learningjames-simon.github.io·1 pts·jxmorris12·0
Philosophical Thoughts on Kolmogorov-Arnold Networks (2024)kindxiaoming.github.io·53 pts·jxmorris12·5
Matmul() using PyTorch's MPs back end is faster than Apple's MLXkevinmartinjose.com·2 pts·jxmorris12·0