Hugging Face has introduced a new feature that allows users to run virtual large language models (vLLMs) directly from Hugging Face Jobs. This means developers can access and utilize vLLMs without the need for local infrastructure or complex setup. The feature is designed to simplify the process of experimenting with and deploying vLLM-based applications. --- Why it matters: This matters because it streamlines the development process for AI researchers and engineers, allowing them to focus on building and testing models rather than managing infrastructure. Source: https://huggingface.co/blog/vllm-jobs