Re:Non-determinism in GPT-4 is caused by Sparse MoE
by PeterisP on Saturday August 05, 2023 @04:20AM
(#37010076)
It's not a code quality issue, there are ways to ensure determinism (sometimes you just need to set a flag), however, they are intentionally explicitly not used in order to gain performance.
[ Parent
| on HN ]
There are no comments on this comment yet.