← Back to context

Comment by pamcake

2 days ago

> All of those where proven harmless for LLM inference.

Could you share link(s) to those proof(s)?

Yup, the tests already compare to a CPU hugginsface implementation, but I'm working on making running and verifying the results of those tests easier and more available. Also, working on fixing those bugs and make the code more reliable now that the underling hardware has been saturated (memory bound)