Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This reads like parody (from llama.cpp, to it being a beacon of where industry is going (!?), to GPUs are overkill for what is effectively a lot of dot products)


Yeah using CPUs for inference or training is ridiculous. We're talking 1/20th the performance for 1/4th the energy




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: