Home Projects mlc-llm
mlc-llm
Python

mlc-llm

Universal LLM Deployment Engine with ML Compilation

by mlc-ai · GitHub
Stars
Forks
License
Created
Last commit
Language
language-modelllmmachine-learning-compilationApache-2.0Python / C++
View on GitHub
In plain words

MLC LLM compiles and runs LLMs natively across GPUs, browsers and mobile devices using machine-learning compilation for hardware-accelerated local inference.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
mlc-llm — GitHub preview card
📈 Star history
23.1k22.9k
2026-06-282026-08-31
📈 Track mlc-llm

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Universal LLM Deployment Engine with ML Compilation

mlc-llm has 23.1k stars on GitHub. It has been forked 2.1k times. mlc-llm is written mainly in Python / C++. It has been in active development since 2023. mlc-llm is available under the Apache-2.0 license. Its main topics are language-model, llm, machine-learning-compilation, tvm.

Read the full guide
Frequently asked questions

What is mlc-llm?

Universal LLM Deployment Engine with ML Compilation

Is mlc-llm open source?

mlc-llm is an open-source project. It is released under the Apache-2.0 license.

Is mlc-llm free?

Yes. mlc-llm is free and open source — you can use, modify and self-host it.

What license does mlc-llm use?

mlc-llm is available under the Apache-2.0 license.

What language is mlc-llm written in?

mlc-llm is written mainly in Python / C++.

🏅 Maintainer of this project?
olud.ai badge — mlc-llm

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=mlc-ai-mlc-llm)](https://olud.ai/project/mlc-ai-mlc-llm.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.