MLC

An Open Community of ML Compilations

What is ML compiler?

A machine learning compiler is a specialized compiler that transforms high-level ML models into optimized code that can efficiently run on various hardware platforms. It bridges the gap between ML frameworks and hardware backends, enabling models to run faster and use less memory across different devices from cloud servers to edge devices.

What is the mission of MLC community?

The MLC community works with the broader ML system ecosystem to enable accessible deployment of ML models across cloud and edge. We aim to democratize ML deployment by providing open-source tools, frameworks, and best practices that make it easier for developers and researchers to deploy models efficiently on diverse hardware platforms.

MLC
Mobile
Desktop
Server
Edge

Featured Projects

MLC LLM

High-performance, memory-efficient LLM inference across devices and backends.

Learn More

WebLLM

In-browser LLM inference on WebGPU with zero server dependency.

Learn More

FlexFlow Serve

Low-latency serving via speculative inference and token tree verification.

Learn More

Mirage

Automated kernel and graph optimization for LLM workloads.

Learn More

XGrammar

Constrained decoding with expressive grammars for structured generation.

Learn More
Loading...
Loading...

Latest Blogs

Loading... Blog

Loading latest blog posts...

Please wait while we fetch the latest articles.

View Blog

The overall community is supported by NSF, CMU Catalyst, Purdue, NVIDIA, Amazon, and Google.