graphcore-research/out-of-the-box-fp8-training

Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.

4 best points · 0 comments · 1 Hacker News post · 46 GitHub stars · View on GitHub

Hacker News discussions

• Out-of-the-box FP8 training (nanoGPT) (4 points, 0 comments, by thecharlieblake, 2023-08-23)