> Sure, they have huge GPU clusters
That's a really, really big "sure."
Almost every trick to run a LLM at OpenAI's scale is a trade secret and may not be easily understood by mere mortals anyways (e.g. bare-metal CUDA optimizations)
That's a really, really big "sure."
Almost every trick to run a LLM at OpenAI's scale is a trade secret and may not be easily understood by mere mortals anyways (e.g. bare-metal CUDA optimizations)
With all the staff poaching the trade secrets may have now leaked?
It's also the reason John Carmack got sued by zenimax when he went to oculus.