Hugging Face Kernels Gets Major Updates for AI Development
Hugging Face has revamped Kernels, expanding support to more AI models and improving the developer experience. The update includes better resource management, smoother integration with Hugging Face Hub, and easier sharing of kernel sessions.
Hugging Face announced major updates to Kernels, its cloud-based tool for running AI models interactively. The revamped Kernels now support a wider range of models from the Hugging Face Hub, offer improved memory and GPU management, and allow users to share their kernel sessions with collaborators more easily.
This update matters because it makes experimenting with AI models more seamless. Instead of managing local environments or juggling dependencies, developers can spin up a kernel in the cloud, select any Hugging Face model, and start running inference or fine-tuning tasks right away. The new interface also streamlines switching between different model sizes and configurations.
If you're curious about Kernels, head over to the Hugging Face website and try running a model like DistilBERT or Gemma-2. Just go to the Kernels section, pick a model, and launch a session to see how easy it is to get started with cloud-based AI experimentation.