GPUs are a critical yet expensive commodity for AI workloads. Justifying their high cost requires maximizing utilization. To keep things in focus, we are not discussing token consumption or tokeneconomics here; This is about GPU optimisation (at the infra and platform). In this post I will describe an approach to building an optimized GPU-as-a-Service using the below key components: GPU Sharing : Increases workload density and optimising GPU usage. Model As A Service (MaaS) : Standardizes and centralizes model deployment and consumption. Kueue : Controls prioritisation, duration and placements of GPU workloads. Self serve : Enables different roles to self serve to utilise GPUs available within the organisation for usecases. GPU Sharing + MaaS + Kueue + Self-Serve = GPU-as-a-Service Solution overview: Demonstration of GPU-as-a-Service in action: Let's dive into the bits now. GPU Sharing: The reason for GPU Sharing is pretty simple. More efficient use of GPUs + Fewer GPUs p...
A simple blog about technical stuffs - technologies, frameworks and processes - The way I see it.