Table 1: Details of FP8 Binary Formats Compares the two formats. For anyone complaining about alt text please read the posts I made.

Notices where this attachment appears

1. Embed this notice
   Ethan Black (golemwire@social.librem.one)'s status on Monday, 06-Jan-2025 05:24:46 JST Ethan Black

   in reply to

   Screenshot from the PDF.

   It appears that #E4M3 (the one without multiple NaNs etc.) has less range, and less precision near 0, but smaller steps between numbers on average.
   E4M3 also has NaN, just one type of NaN (nice).
   I'm not thinking about #deepLearning here in particular, but I think I prefer E4M3 personally (for what it's worth).

   Interesting development. Never thought float8's could have any use, and here we are in 2025 with the potential use of them.

   #computing #programming