Our clients depend on Azure AI infrastructure to develop revolutionary AI-driven options, which is why we’re delivering new cloud-based AI-supercomputing clusters constructed with Azure ND H200 v5 collection digital machines (VMs) right this moment.
The necessity for scalable and high-performance infrastructure continues to develop exponentially because the AI panorama advances. Our clients depend on Azure AI infrastructure to develop revolutionary AI-driven options, which is why we’re delivering new cloud-based AI-supercomputing clusters constructed with Azure ND H200 v5 collection digital machines (VMs) right this moment. These VMs are actually usually obtainable and have been tailor-made to deal with the rising complexity of superior AI workloads, from foundational mannequin coaching to generative inferencing. The dimensions, effectivity and enhanced efficiency of our ND H200 v5 VMs are already driving adoption from clients and Microsoft AI companies comparable to Azure Machine Studying and Azure OpenAI Service.
“We’re excited to undertake Azure’s new H200 VMs. We’ve seen that H200 presents improved efficiency with minimal porting effort, we’re wanting ahead to utilizing these VMs to speed up our analysis, enhance the ChatGPT expertise, and additional our mission.” —Trevor Cai, head of infrastructure, OpenAI.
The Azure ND H200 v5 VMs are architected with Microsoft’s techniques strategy to boost effectivity and efficiency, and have eight NVIDIA H200 Tensor Core GPUs. Particularly, they handle the hole attributable to GPUs rising in uncooked computational functionality at a a lot sooner charge than the connected reminiscence and reminiscence bandwidth. The Azure ND H200 v5 collection VMs ship a 76% enhance in Excessive Bandwidth Reminiscence (HBM) to 141GB and a 43% enhance in HBM Bandwidth to 4.8 TB/s over the earlier era of Azure ND H100 v5 VMs. This enhance in HBM bandwidth allows GPUs to entry mannequin parameters sooner, serving to cut back total software latency, which is a important metric for real-time purposes comparable to interactive brokers. The ND H200 V5 VMs may accommodate extra complicated Giant Language Fashions (LLMs) throughout the reminiscence of a single VM, enhancing efficiency by serving to customers keep away from the overhead of working distributed jobs over a number of VMs.
The design of our H200 supercomputing clusters additionally allows extra environment friendly administration of GPU reminiscence for mannequin weights, key-value cache, and batch sizes, all of which instantly impression throughput, latency and cost-efficiency in LLM-based generative AI inference workloads. With its bigger HBM capability, the ND H200 v5 VM can help larger batch sizes, driving higher GPU utilization and throughput in comparison with ND H100 v5 collection for inference workloads on each small language fashions (SLMs) and LLMs. In early checks, we noticed as much as 35% throughput enhance with ND H200 v5 VMs in comparison with the ND H100 v5 collection for inference workloads working the LLAMA 3.1 405B mannequin (with world measurement 8, enter size 128, output size 8, and most batch sizes – 32 for H100 and 96 for H200). For extra particulars on Azure’s excessive efficiency computing benchmarks, please learn extra right here or go to our AI Benchmarking Information on the Azure GitHub repository for extra particulars.
The ND H200 v5 VMs come pre-integrated with Azure Batch, Azure Kubernetes Service, Azure OpenAI Service and Azure Machine Studying to assist companies get began immediately. Please go to right here for extra detailed technical documentation of the brand new Azure ND H200 v5 VMs.
