MLC AI

MLC AI builds open-source machine learning compilation and deployment tools, with a focus on running LLMs universally across hardware environments. The organization is backed by contributors from CMU Catalyst, UW SAMPL, SJTU, OctoML, and the broader MLC community. Their flagship projects include MLC LLM for native runtime deployment and WebLLM for in-browser inference, both built on Apache TVM. MLC AI prioritizes privacy, cost reduction, and hardware diversity by enabling client-side AI execution without server dependencies.