Entropy of a Large Language Model output

Re:Entropy of a Large Language Model output by HeatrayEnjoyer on Monday January 13, 2025 @11:49AM (#42685477)

Only if the inference software doesn't guarantee concurrency, which is CS 101

[ Parent | on HN ]

Re:Entropy of a Large Language Model output by pizza on Tuesday January 14, 2025 @01:33AM (#42694397)

This sort of nondeterministic scheduling of non associative floating point ops is essentially running at the level of GPU firmware, so, I would imagine that in this case, Nvidia is aware.

[ Parent | on HN ]