alt Hacker NewsFloating point matrix calculations are non-deterministic. You need to invent new hardware, that doesn't use floating point math, first. [0]
Replies
feelamee • today at 3:42 PM
using which floating point standard? IEEE754 is totally deterministic
Floating point matrix calculations are non-deterministic. You need to invent new hardware, that doesn't use floating point math, first. [0]
using which floating point standard? IEEE754 is totally deterministic
>Floating point matrix calculations are non-deterministic.
This is not inherent to floating-point math. That actual (true) claim in the article is that different hardware and different hardware configurations produce different results. But deterministic inference is possible, e.g. llama.cpp on CPU is deterministic by default.