Local LLMs & Inference

Medusa

by FasterDecoding · Jupyter Notebook

Built in Jupyter Notebook, Medusa is an open-source LLM inference tool maintained by FasterDecoding. With 2.8k stars on GitHub, it was last updated in June 2024. Topics include llm and llm-inference.

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

— FasterDecoding, project description on GitHub

Details

CategoryLocal LLMs & Inference
GitHub stars2,775
Forks206
LanguageJupyter Notebook
LicenseApache-2.0
Last updated
OwnerFasterDecoding
Websitesites.google.com/view/medusa-llm
RepositoryFasterDecoding/Medusa

Tags

llmllm-inference

Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.

All Local LLMs & Inference

MTPLX

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in…

Local LLMs & Inference2.6k stars

EAGLE

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Local LLMs & Inference2.6k stars

nanocoder

An open coding agent for your terminal, built by a community collective rather than a company. Bring your…

Local LLMs & Inference2.5k stars

neuron-ai

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect…

Local LLMs & Inference2.1k stars

aici

AICI: Prompts as (Wasm) Programs

Local LLMs & Inference2.1k stars

HyperQwen

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127…

Local LLMs & Inference2.1k stars