[Feature]: Support Embeddings in Infinity

[aguadoenzo]

The Feature

The infinity serving engines offers interesting embedding models (among which CLIP models). The rerank feature is already implemented in the proxy, it would be nice to have the embedding feature as well

Motivation, pitch

I need self-hosted multimodal embeddings, which infinity is great at providing

Are you a ML Ops Team?

No

Twitter / LinkedIn details

No response

[ishaan-jaff]

added to roadmap

[S1LV3RJ1NX]

Support is upcoming: #10009

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.