ModelRefs / MLC-LLM — AI Glossary
MLC-LLM — AI Glossary
A framework for compiling and deploying LLMs natively on diverse hardware (GPU, CPU, mobile) using Apache TVM.
Overview
MLC-LLM (MLC AI, Chen et al. 2023) compiles model weights and compute graphs for specific hardware targets using TVM, achieving near-peak performance without CUDA expertise. Supports: NVIDIA GPUs, Apple Metal (M-series), Vulkan, WebGPU (browser inference). Enables running LLaMA-class models on smartphones and in-browser.
Reference details
| Topic | infrastructure |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to MLC-LLM — AI Glossary.
Frequently asked questions
What is MLC-LLM?
A framework for compiling and deploying LLMs natively on diverse hardware (GPU, CPU, mobile) using Apache TVM.
What concepts are related to MLC-LLM?
Closely related concepts include llama cpp, mlx, edge.