← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

Medusa

github.com

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

LibraryOpen source

Visit github.comexternal siteGitHub2,774 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. sonar

    Large-scale LLM inference engine

    github.comOpen sourcelatest reaction

    GitHub
    1,905 stars

  2. web-llm

    High-performance In-browser LLM Inference Engine

    github.comOpen sourcelatest reaction

    GitHub
    19,361 stars

  3. 1Cat-vLLM

    V100 / SM70-focused vLLM engineering fork for modern LLM inference.

    github.comOpen sourcelatest reaction

    GitHub
    1,477 stars

  4. TileRT

    Tile-Based Runtime for Ultra-Low-Latency LLM Inference

    github.comOpen sourcelatest reaction

    GitHub
    1,887 stars

  5. little-coder

    A harness optimized to smaller LLMs

    github.comOpen sourcelatest reaction

    GitHub
    2,719 stars