Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Medusa: Framework for Accelerating LLM Generation with Multiple Decoding Heads
(github.com/FasterDecoding)
5 points
PaulHoule
2 years ago
discuss
2.
▲
Medusa: Simple Framework for Accelerating LLM Generation
(github.com/FasterDecoding)
1 point
cmitsakis
3 years ago
discuss