vLLM 0.32.0 arrives with Intel GPU builds
The release includes Intel GPU packages and a tagged container. Python support and browser access defaults have changed too.
Version 0.32.0 lists an XPU wheel index and the vllm/vllm-openai-xpu:v0.32.0 container, drops Python 3.10, and restricts default cross-origin (CORS) settings. Before upgrading, check your Python environment and any browser client that connects to the server. We haven't tested this release on the two-B60 setup; the release notes establish neither a speed gain nor a stability improvement here.
The release was published on . Read the upstream release notes for the installation commands and full changes.
Before changing a working setup
Keep the version you're running and its configuration so you can return to it. Test the new build against the same prompts and tools before making it your default.
For the earlier measured setup, see the two-B60 setup guide. Its results apply to the versions recorded there.