float-precision

Tag

Cards List
#float-precision

When adding a fractional part to a number fixes your shader

Lobsters Hottest · 23h ago Cached

The article details the author's debugging journey for a Voronoi-diagram shader, explaining how fractional parts of floats caused animation stutter and the methods used to diagnose and fix the issue.

0 favorites 0 likes
#float-precision

Float Bloat: vector serialization gone wrong

Lobsters Hottest · 2026-08-27 Cached

Bonsai discovered a pervasive issue where embedding vectors are unnecessarily cast from float32 to float64, causing 'Float Bloat' that wastes storage and bandwidth, with an estimated global impact of over 20 Petabytes of overhead.

0 favorites 0 likes
#float-precision

@zcbenz: nvfp4 vs mxfp4 is not just different choices of block size and scale format, nvfp4 uses an additional tensor-wise scale…

X AI KOLs Timeline · 2026-06-17 Cached

A technical comparison between nvfp4 and mxfp4 formats, highlighting that nvfp4 uses an additional tensor-wise scale factor to overcome fp4's range limit, allowing more precision in block-wise scale factors.

0 favorites 0 likes
← Back to home

Submit Feedback