Medusa
PublicMedusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Creat:2023-09-10T14:14:07
Update:2025-03-27T06:46:54
https://sites.google.com/view/medusa-llm
2.6K
Stars
1
Stars Increase
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads