search

tairov / llama2.mojo

Inference Llama 2 in one file of pure 🔥
https://www.modular.com/blog/community-spotlight-how-i-built-llama2-by-aydyn-tairov
MIT License
2.09k stars 139 forks source link

Vectorize temperatures #47

Closed rd4com closed 10 months ago

rd4com commented 10 months ago

Sorry i use github desktop, i had to re-fork

tairov commented 10 months ago

I did some benchmarks and I think this doesn't improve performance, if so, better keep code simpler.

image image image
rd4com commented 10 months ago

oh wow, yes