FasterDecoding/Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

LLM & foundation modelsJupyter Notebook Apache-2.0 207created 2023-09-10

Stars

2,775

1-day growth

—

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

The chart appears after at least 2 days of data.

#llm#llm-inference

Top contributors

Not collected yet (contributors job).

FasterDecoding/Medusa · AI Repo Stats