Skip to content
@FasterDecoding

FasterDecoding

Think deeper, decode faster

Pinned Loading

  1. Medusa Medusa Public

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

    Jupyter Notebook 2.7k 194

Repositories

Showing 5 of 5 repositories
  • REST Public

    REST: Retrieval-Based Speculative Decoding, NAACL 2024

    FasterDecoding/REST’s past year of commit activity
    C 216 Apache-2.0 18 14 0 Updated Mar 5, 2026
  • SnapKV Public
    FasterDecoding/SnapKV’s past year of commit activity
    Python 310 Apache-2.0 30 18 1 Updated Jul 10, 2025
  • TEAL Public
    FasterDecoding/TEAL’s past year of commit activity
    Python 163 MIT 15 5 1 Updated Feb 15, 2025
  • BitDelta Public
    FasterDecoding/BitDelta’s past year of commit activity
    Jupyter Notebook 202 Apache-2.0 16 3 1 Updated Dec 5, 2024
  • Medusa Public

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

    FasterDecoding/Medusa’s past year of commit activity
    Jupyter Notebook 2,722 Apache-2.0 194 51 6 Updated Jun 25, 2024

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

llm llm-inference