login sign up

Speeding up LLM inference 2x times (possibly)

asciinema.org · first added by @hn_wayback
saved by
1 person
discussions · 1
Show HN: Speeding up LLM inference 2x times (possibly) 419 pts · 114 comments · Apr 2024 419 pts · 114 comments · Apr 2024
0 people saved or upvoted this