Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
- ATK
- 2327
- DEF
- 1939
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Drag the card to turn it. Use the flip button to see the back.
Open card page