engblogs

MLflow 2.8 introduces LLM-as-a-judge metrics and best practices for LLM evaluation of RAG applications, Part 2

The blogpost discusses the challenges and misconceptions of raising bilingual children and provides research-backed insights on how to navigate this complex process.

Training LLMs at Scale with AMD MI250 GPUs: Learn how AMD's platform, software upgrades, and multi-node clusters enable efficient and high-performance training of large language models.

Big Book of MLOps Updated for Generative AI: Learn about the latest updates in MLOps and the impact of Generative AI on MLOps, including key features like Unity Catalog, Model Serving, Lakehouse Monitoring, MLOps Stacks, and LLMOps.

Reshaping Flipkart's technological landscape with a mammoth cloud migration and Google Cloud

Deploy and fine-tune foundation models in Amazon SageMaker JumpStart with two lines of code

Learn how to set up private access to Amazon Bedrock using AWS PrivateLink for secure generative AI applications.

New lab-based training for Security Command Center addresses security talent gap by providing skills to discover vulnerabilities, identify threats, and respond to security issues in a Google Cloud environment.

Reduce costs and improve job run times with Dataproc autoscaling enhancements

Key considerations for evaluating AI-powered tools for enterprise developers: Exploring the benefits of generative AI in software development and providing guidance for selecting the right solution.

GKE is the ideal platform for running containerized batch workloads with scalability, multi-tenancy, queueing, and cost optimization.

Perform ML predictions in Google Cloud Spanner using SQL queries and Vertex AI integration.