Show notes
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 ...
Over deze podcast
De Nederlandse Kubernetes Podcast: gemaakt door én voor mensen met een hart voor IT. In deze reeks gaan Ronald Kers en Jan Stomphorst in gesprek over Kubernetes met als doel Kubernetes toegankelijk te maken voor iedereen.
Meer over deze podcastGerelateerde afleveringen
#116 Running AI on Kubernetes: From GPUs to CRO
#123 How Kubernetes and AI are helping prevent wildfires
#132 From CPU to GPU: The New Reality of Kubernetes 1.36
#136: vLLM, LMD, and the Quest to Build the Linux of AI Inference
#135 The Return of OpenStack: Kubernetes & Sovereign Infrastructure
#134 Kubernetes at the Edge: Hype, Reality and Trade-offs
#115 Extending Kubernetes: CRDs, Inheritance & Modularity
#88 Kubernetes on a Tractor: Precision Farming with K3s and Edge AI
Luister verder en doorzoek duizenden podcasts in de Podric-app.
