Updated September 2026, 11 hours ago

Monday highlights from Red Hat Summit 2026

$AI Explained: Reduce GPU costs with LLM Compressor Want to reduce your hardware costs without sacrificing model accuracy? Expert Kyle Sayers joins David to explore the open source LLM Compressor project and explain how model compression lets you run massive models at a fraction of the hardware footprint. ➡️ To learn more and start compressing your own models, visit the LLM Compressor project page: https://github.com/vllm-project/llm-compressor #AIExplained #LLMCompressor #Quantization #MLOps #RedHat #vLLM #AIInference$

Learn about secure enclaves for AI inference

Move VMs forward without holding your business back

60% less time in model training saved $2.5M

How Red Hat cleared IT debt for scalable AI ft. Marco Bill | Technically Speaking with Chris Wright

Deliver at the speed your customers expect. Anywhere.

How gaming netcode handles online player experiences

Red Hat |