GPU Cluster & Inference Tuning with Maaz .
GPU Cluster & Inference Tuning
Maaz Khalid
Maaz is an AI infrastructure architect who builds GPU clusters and air-gapped…
About this session
A 60-minute assisted session for teams building or running GPU infrastructure. We can cover GPU cluster setup and bring-up, Kubernetes scheduling, provisioning and configuration automation, GPU health and monitoring, and LLM inference optimization: model serving choices, GPU utilisation, and throughput, latency and cost trade-offs. Share your GPU types, cluster size, workloads and current bottlenecks when booking.