Why do powerful GPUs sometimes sit idle during #AI inference? Nick Hill tells @kernelcdub about the performance tricks vLLM uses, like speculative decoding and batching, to solve AI's biggest bottleneck and boost throughput. Hear more of vLLM's optimization secrets in the full Technically Speaking episode! → https://t.co/YnEfsNvCvf.
The real value of reasoning LLMs comes in model customization to reason over business data. With @RedHat_AI's synthetic data generation (SDG) capabilities, you can transform unstructured data into high-quality datasets using advanced agentic pipelines. Find out how: https://t.co/ICUtlKE5pB #RHSummit
What's the first thing that comes to mind when tech leaders hear today's top AI & enterprise buzzwords? 🤔 Watch Red Hat CTO @kernelcdub & AI CTO @addvin tackle them in a quick-fire word association game! Don't miss the latest episode of Technically Speaking 🎙️for their deep-dive discussion and expert analysis 🔗 Get the full episode: https://t.co/bZYUz6beGd.
We’re excited to share our plans for IBM Quantum Starling, expected to be the world’s first large-scale, fault-tolerant quantum computer.
This new system, to be delivered to clients by 2029, is expected to perform 20,000x more operations than today’s quantum computers. Read more here: https://t.co/S0ZnuxMKf1
From "any workload, any app, anywhere" to "any model, any accelerator, any cloud." Red Hat CTO @kernelcdub shares how Red Hat’s vision hasn’t changed—it’s evolved. https://t.co/0NM4OcKC0K #RHSummit
We’re hiring a Junior Solution Architect in Switzerland. Are you passionate about open source and AI and ready to kickstart your technical career at Red Hat?
Join our passionate TechSales team: https://t.co/SjmlMDfAyH
From "any workload, any app, anywhere" to "any model, any accelerator, any cloud." Red Hat CTO @kernelcdub shares how Red Hat’s vision hasn’t changed—it’s evolved: https://t.co/yvatc0qmGy #RHSummit
Our vision for AI is this: any model, any accelerator, any cloud. This is the next chapter in enterprise AI, and we’re excited to build it with you. #RHSummit
Unlock productivity and make OpenShift more accessible for users at any skill level with Red Hat OpenShift Lightspeed. Now generally available. This generative AI-powered assistant helps accelerate learning, boost accuracy and efficiency, and frees up IT teams to focus on innovation. https://t.co/n6754OSnUZ
#RHSummit
Big news from Red Hat! We’ve just launched the hashtag#LLM-d Community, a groundbreaking hashtag#openSource initiative that brings distributed Gen AI inference to production scale. We aim to make it as ubiquitous and foundational as Linux.
This community is the result of deep collaboration with amazing founding contributors: CoreWeave, Google Cloud, IBM Research, and NVIDIA, and has already attracted support from leaders across the ecosystem: AMD, Cisco, Hugging Face,Intel Corporation, Lambda, Mistral AI, and top academic minds at UC Berkeley and University of Chicago.
Why does this matter? Gen AI is at an inflection point. To truly unlock its potential in the enterprise, we need a scalable, efficient, and open infrastructure. hashtag#llm-d delivers that by enabling high-performance, distributed inference across heterogeneous environments.
Proud to see Red Hat once again at the forefront of open innovation.
Let’s shape the future of AI together.
https://t.co/0f302Mz5iG
I’m excited to share that the City of Vienna has been nominated for the Red Hat Innovation Awards! This is a remarkable success story of how a 1,000-year-old city is transforming its administrative services with Red Hat AI technologies.
https://t.co/MpFzlLangj