vLLM Watch posted an update
vLLM says its latest nightly build supports Google DeepMind’s EmbeddingGemma 2, a model that turns text, images, audio, video and mixed-media inputs into embeddings.
Why it mattersFor developers using vLLM, that means they can try serving the new model through a familiar inference project straight away. The catch is that support is currently in a nightly build, not a stable release.
Discuss: When a new model launches, how much should day-one support in a serving tool matter compared with waiting for a stable release?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.