The Best Choice for AI Inference: vLLM

Why vLLM's open-source architecture, advanced KV-cache management, and parallelization strategies make it the best choice for production LLM inference.

Posted on October 9, 2025

Eight Lessons on Open Source Leadership and Community

What contributing, mentoring, and stewarding have taught me about OSS

Lessons on stewardship, trust, mentoring, and community building from years of contributing to and leading open source projects.

Posted on September 20, 2025

PyTorch on Kubernetes: Kubeflow Trainer Joins PyTorch Ecosystem

Kubeflow Trainer joins the PyTorch ecosystem, providing Kubernetes-native distributed training and LLM fine-tuning with simplified APIs.

Posted on July 28, 2025

Announcing KServe v0.15: Advancing Generative AI Model Serving

KServe v0.15 introduces enhanced generative AI model serving with Envoy AI Gateway integration, multi-node inference, and LLM autoscaling with KEDA.

Posted on May 27, 2025

Introducing vLLM Inference Provider in Llama Stack

Introducing the vLLM inference provider in Meta's Llama Stack, with a tutorial for local and Kubernetes deployment.

Posted on January 26, 2025

Reading Notes: The Manager's Path - A Guide for Tech Leaders Navigating Growth and Change

Reading notes on The Manager's Path — covering management fundamentals, mentoring, tech lead roles, and engineering leadership growth.

Posted on January 1, 2025

AI/ML Innovation in the Kubernetes Ecosystem

Recent innovations like the Model Registry, ModelCars feature, and TrustyAI are delivering manageability, speed, and accountability for AI/ML workloads

How innovations like Model Registry, ModelCars, and TrustyAI in the Kubeflow and KServe ecosystem are making AI/ML production-ready on Kubernetes.

Posted on October 22, 2024

Reading Notes: Staff Engineer - Leadership beyond the Management Track

Reading notes on Staff Engineer: Leadership beyond the Management Track — archetypes, operating at staff level, and navigating the career path.

Posted on June 24, 2024

From Serverless Predictive Inference to Generative Inference - Introducing KServe v0.13

KServe 0.13 Release Blog Post

KServe v0.13 evolves cloud-native model serving for generative AI with enhanced Hugging Face runtime, vLLM backend support, and OpenAI protocol integration.

Posted on May 15, 2024

Open Source AI at Red Hat: Our Journey in the Kubeflow Community

Red Hat's journey contributing to the Kubeflow community — from Open Data Hub integration to KServe improvements and the Kubeflow 1.9 release.

Posted on March 19, 2024