All about Switching to a Local LLM in VS Code

Since version 1.116, GitHub Copilot Chat is a built-in extension in Visual Studio Code (VS Code). That means Copilot features such as chat, inline suggestions, and agents are now an integral part of VS Code. AI-assisted programming tools like GitHub Copilot have transformed software development workflows, yet reliance on proprietary cloud endpoints raises critical concerns regarding data privacy, intellectual property protection, network dependency, and recurring operational costs. For academic and high-performance computing researchers working with sensitive datasets or proprietary codebases, keeping code analysis entirely on-premises is often non-negotiable.

This webinar explores how to bridge local large language model (LLM) inference engines with modern development environments, focusing on integrating self-hosted models into VS Code, with or without GitHub Copilot. Even if data privacy is not your concern, as will be demonstrated in this webinar, a local LLM enables you to do more with less by substantially reducing your AI credit usage.

Familiarity with VS Code and basic terminal commands is recommended, but no prior experience with LLM deployment is required.