Envoy AI Gateway Ushers in a New Era with MCP Integration AI workloads are evolving fast, and Envoy AI Gateway’s integration of the Model Context Protocol (MCP) is a major leap for organizations leveraging modern, production-scale AI systems. Jointly develop... AI agents Envoy Gateway gateway security Kubernetes MCP OAuth open standards tool routing
Postgres 18: Major Advances in Performance, Security, and Flexibility For developers choosing the right database is critical in today’s fast-paced, data-centric world. Postgres 18 answers the call for speed, enhanced security, and seamless integration, making it a compe... asynchronous I/O database Kubernetes OAuth open source Postgres 18 security SQL standards
Smarter LLMs: How the vLLM Semantic Router Delivers Fast, Efficient Inference Large language models are evolving rapidly. Instead of simply increasing their size, innovators now focus on maximizing efficiency, reducing latency, and assigning compute resources according to query... enterprise AI Kubernetes latency optimization LLM inference model efficiency open source AI semantic routing
How John Lewis Revolutionized Developer Experience with Platform Engineering In 2017, John Lewis , a leading UK retailer, confronted the challenges of its aging monolithic e-commerce platform. Hampered by sluggish release cycles and complex cross-team dependencies, the organiz... developer experience DevOps e-commerce Google Cloud Kubernetes microservices multi-tenant platform engineering
Docker Compose Provider Services Are Streamlining Development For years, Docker Compose has been a staple for developers wanting to spin up multi-container environments locally. Now, with the addition of provider services in Docker Compose v2.36.0 the evolution ... cloud integration Compose devops Docker Kubernetes plugins provider services
vLLM Is Transforming High-Performance LLM Deployment Deploying large language models at scale is no small feat, but vLLM is rapidly emerging as a solution for organizations seeking robust, efficient inference engines. Originally developed at UC Berkeley... AI inference GPU optimization Kubernetes large language models memory management model deployment vLLM