login sign up

Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x

hao-ai-lab.github.io · first added by @hn_wayback
saved by
1 person
discussions · 1
Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x 461 pts · 98 comments · May 2024 461 pts · 98 comments · May 2024
0 people saved or upvoted this