News for hackers. Stuff that matters.

A comment on Non-determinism in GPT-4 is caused by Sparse MoE. Parent comment

Re:Non-determinism in GPT-4 is caused by Sparse MoE by WithinReason on Saturday August 05, 2023 @03:01AM (#37009680)
That summation is slow and would not be used in practice.

You could use just one thread on your 10000 thread GPU too and it would be deterministic, sure. Completely beside the point.

[ Parent | on HN ]

There are no comments on this comment yet.