Nutanix complements its existing on-prem, Kubernetes and edge AI offerings with a public cloud offering which becomes a part of Nutanix GPT-in-a-Box 2.0.
Lee Caswell, SVP of Product and Solutions Marketing at Nutanix
At the recent KubeCon event, hybrid multicloud computing vendor Nutanix has announced Nutanix Enterprise AI (NAI), which extends the company’s AI infrastructure into the public cloud. The NAI offering provides a consistent hybrid multicloud operating model for accelerated AI workloads, which helps organizations to leverage their models and data in a secure location of their choice while securely deploying running and scaling inference endpoints for large language models (LLMs). This supports the deployment of GenAI applications in minutes rather than days or weeks.
NAI provides a consistent multicloud operating model and a simple way to securely deploy, scale and run LLMs with NVIDIA NIM optimized inference microservices as well as open source foundation models from Hugging Face. This enables customers to stand up enterprise GenAI infrastructure with the resiliency, day 2 operations, and security they require for business-critical applications, on-premises or on AWS Elastic Kubernetes Service (EKS), Azure Managed Kubernetes Service (AKS), and Google Kubernetes Engine (GKE).
“We have had Predictive AI for years,” said Lee Caswell, SVP of Product and Solutions Marketing at Nutanix. “But Generative AI is new for us. Customers are thinking carefully about where they are putting AI for inferencing, and where they want to run these over time. Two parts of GenAI are changing very fast – hardware and LLM. GenAI is the next critical business application, while data privacy and protection are also of critical importance.
Caswell said that differentiation is critical for GenAI
“There is always a desire to have a choice,” he stated. “There is always some lock in, but switching costs are low for parts that might change. You can also start it in the public cloud and later move it to GPUs that you run, or you can run it on your choice of hyperscalers. Caswell also stressed that Nutanix Enterprise AI delivers a transparent and predictable pricing model based on infrastructure resources, which is important for customers looking to maximize ROI from their GenAI investments. This is in contrast to most cloud services that come with complex metering and hard-to-predict usage-based pricing. In addition, simplicity and, choice mean IT admins can be AI admins, accelerating AI development by data scientists and developers adapting quickly using the latest models and NVIDIA accelerated computing. Hugging Face and other model standards are also supported, and filters task by name with one integration from Nutanix and access with a single integration point Additionally, native integration with Nutanix Kubernetes Platform keeps alignment with the ability to leverage the entire Nutanix Cloud Platform or provide customers with the option to run on any Kubernetes runtime, including AWS EKS, Azure AKS, or Google Cloud GKE with NVIDIA accelerated computing.
Key use cases for customers leveraging Nutanix Enterprise AI include: enhancing customer experience with GenAI through analysis of customer feedback and documents; accelerating code and content creation by leveraging co-pilots and intelligent document processing; leveraging fine-tuning models on domain-specific data to accelerate code and content generation; strengthening security, including leveraging AI models for fraud detection, threat detection, alert enrichment, and automatic policy creation; and improving analytics by leveraging fine-tuned models on private data.
