LLMs Don't Have to Generate One Token at a Time: How Medusa and Multi-Token Prediction Cheat Autoregression
DEV Community
LLMs Don't Have to Generate One Token at a Time: How Medusa and Multi-Token Prediction Cheat Autoregression
Hello, I'm Shrijith Venkatramana, and I'm building LiveReview — a blast-radius aware AI code review...
0 comments
No comments yet.