Scaling AI inference with open source ft. Brian Stevens | Technically Speaking with Chris Wright скачать в хорошем качестве

Scaling AI inference with open source ft. Brian Stevens | Technically Speaking with Chris Wright

How are enterprises re-imagining AI for real-world impact? Chris Wright, Red Hat CTO and SVP Global Engineering sits down with Brian Stevens, Red Hat SVP and AI CTO, to discuss the journey towards production-quality AI inference at scale. They explore the critical role of open source projects like vLLM, the evolution from CPU to GPU optimization, and the parallels between today's AI challenges and the early days of enterprise Linux. 00:00:37 - Brian Stevens on returning to Red Hat & parallels with early Linux 00:02:00 - The path from cloud to AI & the impact of ChatGPT 00:03:58 - Pivoting to GPUs & the rise of vLLM for generative AI 00:05:48 - From CPU sparsification to GPU model compression 00:08:00 - Optimizing for modern GPUs with vLLM 00:11:38 - An ""AI Operating System""? Integrating vLLM with Kubernetes 00:15:31 - vLLM: A common platform for diverse AI hardware & models 00:17:41 - The importance of distributed KV cache for scalable inference 00:22:53 - Inference-time scaling, reasoning, and platform Demands 00:25:10 - Ecosystem & Community: The key to AI's future Learn More: Red Hat AI Solutions: https://www.redhat.com/en/products/ai vLLM Project: https://docs.vllm.ai/ vLLM GitHub: https://github.com/vllm-project/vllm Follow us: Chris Wright (LinkedIn):   / chris-wright-b733851   Brian Stevens (LinkedIn):   / brianmarkstevens   What is Technically Speaking? Technically Speaking taps into emerging technology trends with insights from leading experts across the globe and Red Hat CTO Chris Wright. The series blends deep-dive discussions, tech updates, and creative short-form content, solidifying Red Hat’s role as a pioneer in technology innovation and open source thought leadership. Want to participate? Leave us a comment if there's a topic or a guest you'd like to see featured. Watch More Technically Speaking: YouTube playlist:    • Technically Speaking with Chris Wright   Show Page: https://www.redhat.com/en/technically... Subscribe to Red Hat's YouTube channel: https://www.youtube.com/redhat/?sub_c... #RedHat #TechnicallySpeaking #AIInference #vLLM #EnterpriseAI #OpenSource #BrianStevens #PracticalAI #llmd"