"The setup is straightforward. Install the Hugging Face Copilot Chat extension, open VS Code's chat interface, select Hugging Face as your provider, add your token, and choose your models. Once connected, you can switch between different providers and models using the same interface you're already familiar with. There's one catch worth noting early: you need VS Code version 1.104.0 or newer. AI researcher Aditya Wresniyandaka pointed this out after the initial announcement, noting that the documentation missed this requirement."
"GitHub Copilot Chat has always used a limited set of proprietary models. Now it can tap into Hugging Face's network of hundreds of inference providers. This provides developers with access to experimental models, specialized tools, and open-source alternatives that were previously unavailable. Muhammad Arshad Iqbal captured the appeal: "Now we can use all those powerful open-source coding AIs right inside VS Code. No more switching tabs just to test a model like Qwen3-Coder." The real value is choice. Instead of being stuck with whatever GitHub provides, you can pick models optimized for specific programming languages, industries, or research areas."
Hugging Face released a VS Code extension that integrates open-source large language models with GitHub Copilot Chat. Installation requires adding the Hugging Face Copilot Chat extension, selecting Hugging Face as the provider, supplying a token, and choosing models. Once connected, users can switch between providers and models inside VS Code's chat interface. VS Code version 1.104.0 or newer is required. The integration expands access beyond proprietary models to hundreds of inference providers, offering experimental, specialized, and open-source alternatives. Developers can test language- or domain-specific coding models inside the editor, reducing workflow friction and accelerating experimentation.
Read at DevOps.com
Unable to calculate read time
Collection
[
|
...
]