Releasesby IbisElastic looks to speed up Jina Model Inference by 8x using NVIDIA RTX GPUs
Update3 days agoUnverifiedAdded Oct 22, 2026
Elastic improved Jina model inference performance by up to 8x for embeddings, 4x for reranking, and 3.7x for OCR using NVIDIA RTX Pro 6000 GPUs.
Topics: LLMs, Performance
More Elastic releases
Every Elastic releaseElastic Stack 9.5.5 released
Elastic has released version 9.5.5 of the Elastic Stack, which includes bug fixes and changes over the previous version 9.5.4.
Elastic Stack 9.4.8 released
Elastic has released version 9.4.8 of the Elastic Stack, which includes bug fixes and changes over the previous version 9.4.7.
Elastic Stack 8.19.23 released
Elastic has released version 8.19.23 of the Elastic Stack, which includes bug fixes and changes over the previous version 8.19.22.
Bring your own key to existing Elastic Cloud deployments
Elastic Cloud now allows users to encrypt data and snapshots using their own KMS keys on existing deployments. This update enables encryption in place without requiring the recreation of the deployment.
Elastic Cloud Serverless: Another Azure region
Elastic Cloud Serverless is now available in the Microsoft Azure Iowa region. This expansion brings the total number of supported serverless Azure regions to 12.
Elastic Cloud on Azure gets a speed boost: Compute-optimized instances on Azure Cobalt ARM
Elastic Cloud on Azure has added compute-optimized hardware profiles powered by Microsoft's Cobalt ARM processors, delivering up to 37% better throughput at a lower cost.
Elastic Stack 8.19.22 released
Elastic released Elastic Stack version 8.19.22, providing bug fixes and maintenance improvements over version 8.19.21.
Elastic announces GA of cross-project search on Serverless, enabling teams to query across all linked projects without moving a byte
Cross-project search is now GA on Elastic Cloud Serverless. Link multiple projects and query all of them from a single Discover or ES|QL session: no certificates, no remote cluster config, and three clicks to set up. Available from September 1, 2026.
Also shipped on Oct 21, 2026
Elastic in October 20262026.10.09
The voice catalog grows from about 390 to more than 1,400 voices. The 1,035 new voices span all five languages and 29 accents, for use cases from customer service to characters. Browse them in the Studio voice library or read the announcement . Also new in Studio : Preview samples: a voice can have several preview samples, each reading a different sentence.
The AI.CHUNK_DOCUMENT function is a table-valued function that splits unstructured documents into...
The AI.CHUNK_DOCUMENT function is a table-valued function that splits unstructured documents into semantically coherent text chunks optimized for vector embeddings and Retrieval-Augmented Generation (RAG) workflows. This function is generally available (GA).
Automated cataloging and ingestion of Looker (Google Cloud core) metadata with Knowledge Catalog is now...
Automated cataloging and ingestion of Looker (Google Cloud core) metadata with Knowledge Catalog is now generally available (GA). This includes support for additional granular metadata (including dimension/measure definitions, default queries, and relationships) and new asset types: LookML dashboards, LookML dashboard elements, and agents.
Screen MCP tool calls and results for jailbreaks (Beta)
You can now screen MCP tool calls and their results in Unity Gateway for jailbreak and prompt injection attempts. Apply the Jailbreak guardrail on input, output, or both. See Attach a built-in policy .
[Launched] Generally Available: Azure Cosmos DB Safe Key Rotation
Safe Key Rotation for Azure Cosmos DB is now generally available. You can view timestamp metadata showing when each account key was last used, helping you identify active keys before rotating or retiring credentials.This visibility helps reduce the risk o
OpenAI models are coming to Google Cloud
OpenAI frontier models and Codex workflows are now available in Google Cloud's Model Garden via the Google Cloud Marketplace.