In this episode, we talk with Abdel Sghiouar and Mofi Rahman, Developer Advocates at Google and (guest) hosts of the Kubernetes Podcast from Google. Together, we dive into one central question: can you truly run LLMs reliably and at scale on Kubernetes? It quickly becomes clear that LLM workloads behave nothing like traditional web applications: GPUs are scarce, expensive, and difficult to schedule.Models are massive — some reaching 700GB — making load times, storage throughput, and caching ...
All content for De Nederlandse Kubernetes Podcast is the property of Ronald Kers en Jan Stomphorst and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
In this episode, we talk with Abdel Sghiouar and Mofi Rahman, Developer Advocates at Google and (guest) hosts of the Kubernetes Podcast from Google. Together, we dive into one central question: can you truly run LLMs reliably and at scale on Kubernetes? It quickly becomes clear that LLM workloads behave nothing like traditional web applications: GPUs are scarce, expensive, and difficult to schedule.Models are massive — some reaching 700GB — making load times, storage throughput, and caching ...
In this episode of De Nederlandse Kubernetes Podcast, we talk with Carlos Santana, Principal Partner Solution Architect at AWS and long-time contributor to the Kubernetes and AI communities. Carlos joins us to explore what it really takes to run AI workloads on Kubernetes, from GPU scheduling to scaling inference and training efficiently across clusters. We discuss how AI and machine learning are transforming the cloud-native ecosystem — and why orchestration is becoming just as important as ...
De Nederlandse Kubernetes Podcast
In this episode, we talk with Abdel Sghiouar and Mofi Rahman, Developer Advocates at Google and (guest) hosts of the Kubernetes Podcast from Google. Together, we dive into one central question: can you truly run LLMs reliably and at scale on Kubernetes? It quickly becomes clear that LLM workloads behave nothing like traditional web applications: GPUs are scarce, expensive, and difficult to schedule.Models are massive — some reaching 700GB — making load times, storage throughput, and caching ...
