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 ...
#107 CloudNativePG Operator: de brug tussen Open Source, databasebeheer en AI
De Nederlandse Kubernetes Podcast
34 minutes
3 months ago
#107 CloudNativePG Operator: de brug tussen Open Source, databasebeheer en AI
In deze aflevering spreken we met Farshad Poye, verantwoordelijk voor de Nederlandse markt bij EnterpriseDB, en Driss Chhayra, die binnen EDB de EMEA-markt aanstuurt. Ze nemen ons mee in de groei van PostgreSQL binnen Kubernetes, de rol van open source in hybride infrastructuur én hoe AI dichter bij je data komt te staan dan ooit. We blikken terug op de ontwikkelingen sinds hun eerdere (meest beluisterde!) aflevering, EDB’s operator is nu als sandbox opgenomen in de CNCF, en biedt met CloudNa...
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 ...
