Blog
1359+ articles — Page 2 of 57
GPUs Take Flight: Multi-Tenant Platform Engineering at
I presented safety-first multi-tenant GPU platform engineering with NVIDIA and Red Hat OpenShift AI at Red Hat Summit 2026 Discovery Theater in Atlanta.
Luca Berton •
Starweaver AI in Professional Education Summit 2026: AI
Panel discussion at the Starweaver AI in Professional Education Summit on AI agents that onboard, coach, and upskill without a human in the loop.
Luca Berton •
AI-Powered RHEL Management with MCP Servers at Red Hat
Hands-on lab at Red Hat Summit 2026 — managing RHEL fleets with Model Context Protocol servers for Lightspeed and Satellite, presented by Nathan Kinder.
Luca Berton •
Meeting Chris Wright: CTO of Red Hat at Summit 2026
A personal encounter with Chris Wright, CTO of Red Hat, at Red Hat Summit 2026 in Atlanta — discussing open source AI, the future of enterprise Linux, and.
Luca Berton •
Upgrading to OpenShift AI 3.x at Red Hat Summit 2026
Version history, support windows, supported configurations, and a 5-step migration framework for upgrading from RHOAI 2.x to 3.x — from Red Hat Summit 2026.
Luca Berton •
OpenShift Virtualization Storage at Red Hat Summit 2026
Storage decision trees, CSI driver testing, and PVC gotchas from the OpenShift Virtualization storage session at Red Hat Summit 2026 in Atlanta.
Luca Berton •
Building Digital Sovereign AI: Red Hat and MetaX at Red
Li Ming Tsai and Jiaju Zhang present China's sovereign AI stack at Red Hat Summit 2026 — MetaX GPUs, Qwen/DeepSeek at 30% global token usage, and the.
Luca Berton •
Red Hat Summit 2026 Keynote: Eight Announcements That Matter
NASA, Fedora Hummingbird, Red Hat Desktop, Hardened Images, OpenShell, RHEL Long-Life Add-On, and the NVIDIA partnership from Summit 2026.
Luca Berton •
13 Things I Heard at Red Hat Summit 2026
Real conversations from the Red Hat Summit 2026 floor in Atlanta — the pain points, gaps, and needs enterprises actually have with OpenShift, Kubernetes.
Luca Berton •
Operationalizing OpenShift Virtualization at Red Hat
Hands-on workshop covering VM lifecycle, hardware optimization, resilience, and advanced live migration strategies on OpenShift Virtualization.
Luca Berton •
Red Hat AI Factory with NVIDIA: Confidential Compute and
Inside the Red Hat and NVIDIA joint session at Summit 2026 — confidential compute threat models, AI Factory workload projection with HGX B200/300 and RTX.
Luca Berton •
AgentOps in Production: Hands-On Lab at Red Hat Summit 2026
Inside the AgentOps hands-on lab at Red Hat Summit 2026 — agentic end-to-end observability with Red Hat AI, featuring Roberto Carratala, Taylor Smith, and.
Luca Berton •
bootc Image Plus Config: Managing OS Configuration at Scale
How to combine bootc immutable OS images with runtime configuration for production Linux. Build the golden image, layer site-specific config, and update.
Luca Berton •
Immutable Linux with bootc: Atomic Updates and Rollback
How bootc brings container-native image mode to Linux. Atomic OS updates, instant rollback, and why immutable infrastructure is the future of production.
Luca Berton •
Forward Deployed Engineer: The Role Bridging Engineering
What is a Forward Deployed Engineer and why top tech companies are hiring them. The hybrid role that combines software engineering, consulting, and.
Luca Berton •
llm-d at Red Hat Summit 2026: KV-Cache Aware Routing for
Red Hat presented llm-d at Summit 2026 — cache-aware load balancing for multi-pod vLLM deployments. Cold 4.3s vs warm 0.6s (7x faster), $0.30 vs $3.00 per.
Luca Berton •
Mistral Small 4 119B: One Model, Three Personalities
Mistral Small 4 unifies instruct, reasoning, and coding into a single 119B MoE model with 128 experts, 6.5B active per token, 256K context, and Apache 2.0.
Luca Berton •
Wide Expert Parallelism on NVL72: Scaling MoE Inference
How NVIDIA TensorRT-LLM Wide-EP distributes MoE experts across GB200 NVL72 racks for 1.8x per-GPU throughput on DeepSeek-R1 scale models.
Luca Berton •
Red Hat Training Hub: Unified LLM Fine-Tuning at Summit 2026
Red Hat AI Innovation Team unveiled Training Hub at Red Hat Summit 2026 — a unified Python API for SFT, LoRA, OSFT, and GRPO fine-tuning with MLFlow.
Luca Berton •
vLLM Recipes: Deploy Any Model on Any GPU
Community-maintained vLLM serve configurations for every major model on NVIDIA H100/H200/B200, Grace-Blackwell, and AMD MI300X/MI325X hardware.
Luca Berton •
Red Hat Summit 2026 in Atlanta: Open Source Meets AI at
My experience at Red Hat Summit 2026 in Atlanta — from platinum sponsors to late-night labs, product spotlights, and Turkish Airlines scaling 60+ AI.
Luca Berton •
Fix Astro Build Out-of-Memory on GitHub Actions: Bump
Astro builds with heavy image optimization can OOM on GitHub Actions runners with exit code 134. Set NODE_OPTIONS=--max-old-space-size=6144 on the build.
Luca Berton •
Free Practical RHEL AI Book at Red Hat Summit 2026
I am giving away copies of my latest book Practical RHEL AI at Red Hat Summit 2026 in Atlanta. Meet me at the Lawn Lounge at 16:45 to grab your free copy.
Luca Berton •
Checkmarx at DevWorld 2026: AI Is Not Enough for AppSec
Checkmarx presented a compelling case at DevWorld Conference 2026: AI-only security scanning creates noise, not safety. The hybrid approach combining.
Luca Berton •