AI performance extends beyond chip metrics; it relies on integrated hardware, software, and infrastructure. Traditional benchmarks fall short, so NVIDIA DGX Cloud Benchmarking offers a standardized framework to evaluate large-scale AI workloads. NVIDIA and Azure present an end-to-end benchmarking workflow, sharing optimization strategies for deploying and tuning production-ready LLMs on Azure.
talk-data.com
J
Speaker
Jer-Ming Chia
1
talks
Jer-Ming Chia is a Principal TPM Manager at Microsoft, where he leads a team of system architects and TPMs focused on enabling AI customers to run large-scale workloads on Azure. With deep experience in HPC, distributed systems, and operational strategy, Jer-Ming works at the intersection of engineering and customer success to deliver reliable, high-performance platforms for advanced AI applications.
Bio from: Microsoft Ignite 2025
Filter by Event / Source
Talks & appearances
1 activities · Newest first