vLLM announced day-0 support for EmbeddingGemma 2 from Google DeepMind, a bidirectional omni-modal embedding model that maps text, image, audio, video, and interleaved inputs into one vector space.
Users can try it with the latest vLLM nightly build using the command vllm serve google/embeddinggemma-2 --runner pooling. The quoted Google post says the model is built on the Gemma 4 architecture and released under Apache 2.0.
🎉 Excited to support EmbeddingGemma 2 from @GoogleDeepMind on day 0!
This bidirectional omni-modal embedding model maps text, image, audio, video, and interleaved multimodal inputs into a vector space for various use cases!
Try it out with the latest nightly build of vLLM!
We’re releasing EmbeddingGemma 2, our first natively multimodal open model engineered for on-device embeddings. Built on the Gemma 4 architecture and released under an Apache 2.0 license, it goes beyond text to unify images, video, audio, and code in a single embedding space.
Source: vLLM · x.comPublished · added here
