GPUs go brrr! Elastic Inference Service (EIS): GPU-accelerated inference for Elasticsearch

Elastic has announced the Elastic Inference Service (EIS), a new GPU-accelerated "inference-as-a-service" natively integrated with Elasticsearch on Elastic Cloud. Utilizing NVIDIA GPUs, the service provides scalable, low-latency access to models for embeddings, reranking, and LLMs, significantly reducing the operational complexity of managing AI workloads. While currently featuring ELSER in technical preview, Elastic plans to expand the service with more diverse models and broader regional availability.