With this software, Machine Learning Engineers can deploy models for experimental purposes enabling rapid iteration, which is essential for understanding model behavior, visualization, and debugging. Due to the intuitive interface users do not need extensive Kubernetes experience, creating a simplified path to production model deployments for everyone. ITOps/MLOps can take the models developed by the MLE team and deploy them quickly at scale. HPE Machine learning Inference Software has a broad range of supported frameworks, automation to help you deploy swiftly, and is suitable for both development and production environments. Users can manage their model deployments with efficient load balancing for better scalability, consistent performance, and robust error handling with automated testing.

HPE Machine Learning Inference Software is the third and final component completing the vision “…to build the world’s best platform for developing and deploying AI applications at scale”, along with HPE Machine Learning Data Management Software and HPE Machine Learning Development Environment Software. HPE Machine Learning Inference Software is differentiated by embracing flexibility and cost efficiency and shunning proprietary tools and mitigating escalating costs. It avoids vendor lock-in, fostering seamless multi-cloud compatibility.

HPE Machine Learning Inference Software does not require extensive education as the platform is intuitive and easy to learn. No need to assemble multiple tools to start your AI journey – HPE Machine Learning Inference Software provides comprehensive solutions tailored to customer needs and, robust integrations with open source and proprietary tools ensure resilient and secure operations, while our adaptive approach effortlessly accommodates technological advancements.

With HPE Machine Learning Inference Software, you're not confined to a single focus; it offers versatile solutions for diverse model deployment requirements and integration with NVIDIA Inference Microservices (NIM) to provide optimized inference for more than two dozen popular downloadable AI models from NVIDIA and its partner ecosystem.

Product Benefits

• – Deploy AI/ML models to the datacenter or cloud
• – Enterprise-grade security with RBAC and secure authentication for endpoints.
• – Seamless integration with NVIDIA NIM
• – Diverse framework compatibility for models you create or import.
• – Workload optimization for underlying hardware, eliminating manual tuning
• – Comprehensive monitoring and management for AI model health and performance
• – Streamlined setup via industry-standard Helm charts

Seamless integration with NVIDIA Inference Microservices (NIM)

Leverages NVIDIA’S optimized inference microservices for efficient model deployment at scale, offering unparalleled inference speeds, reducing time to insights. Pre-trained models from NVIDIA and their partner ecosystem can directly imported and used without further optimization.

Diverse Model Framework Compatibility

Facilitates using models from diverse frameworks such as TensorFlow, PyTorch, scikit-learn, and XGBoost, accommodating a broad range of pre-trained and custom models.

Model Packaging

Streamlined integration with Hugging Face and NVIDIA Foundation Models offers a zero-coding deployment experience for large language models (LLMs) directly from Hugging Face and NVIDIA NGC.

Customized models can utilize built-in containerization tools to ensure a streamlined, consistent, and version-controlled deployment process.

Monitoring and Management

Benefit from integrated monitoring and logging for tracking model performance, usage metrics, and system health, facilitating proactive optimization.

Security

Execute workloads within your preferred environment, thus ensuring the security of your models, code, and data. Implement Role-Based Access Controls (RBAC) to securely manage how development and MLOps teams access and share machine learning resources and artifacts.

Enable authentication on your model endpoints to manage access to your inference services including OIDC and OAuth 2.0 with flexible integration options.

Versatile Deployment

Compatible with Kubernetes-supported environments, including major cloud services like GreenLake, AWS, Azure, Google Cloud, and on-premises setups, ensuring flexible integration across diverse infrastructures.

Seamless Scaling

Handle deployment scaling based on the requested load to meet your needs, utilizing built-in mechanisms to automatically scale containers and manage traffic.

Product Licenses

HPE Machine Learning Inference Software must be licensed to allow software download and support from HPE.

Licensing and Renewals follow a two-tier model:

• – Base License: Licenses the installation of HPE Machine Learning Inference Software on an OS instance (physical, virtual, or cloud based) and includes 1 Performance license.
• – Performance License: Licenses GPU/Accelerator for use with HPE Machine Learning Inference Software

If the licensing rules are unclear for your specific usage, please contact the local HPE or authorized partner sales representative before ordering.

Step 1 – Calculate the number of Base licenses:

• – One base license is required per OS instance ( a single running install of an OS, whether physical, virtual, or cloud based)
• – Select the appropriate tenure of subscription for that enterprise license (1-, 3-, 4- and 5-year terms are available).
• – Customers can acquire their entitlements certificates from the HPE Software Portal.
• – Base licenses include 1 performance license

HPE Support

HPE Tech Care Service enables direct access to product-specific specialists and provides general technical guidance to help customers not only reduce risk but also find ways to do things more efficiently. HPE Tech Care Service Customers can access support through multiple channels that include telephone, a real-time chat facility, automated incident logging, and HPE moderated forums with defined response times.

HPE 1Y Tech Care Basic Service

• – Expert access: 9x5, 2hr response
• – Outage SLA: Standard elevation

HPE Services

No matter where you are in your digital transformation journey, you can count on HPE Services to deliver the expertise you need when, where and how you need it. From planning to deployment, ongoing operations and beyond, our experts can help you realize your digital ambitions.

https://www.HPE.com/services

Consulting Services

No matter where you are in your journey to hybrid cloud, experts can help you map out your next steps. From determining what workloads should live where, to handling governance and compliance, to managing costs, our experts can help you optimize your operations.

https://www.HPE.com/services/consulting

HPE Managed Services

HPE runs your IT operations, providing services that monitor, operate, and optimize your infrastructure and applications, delivered consistently and globally to give you unified control and let you focus on innovation.

HPE Managed Services | HPE

Operational services

Optimize your entire IT environment and drive innovation. Manage day-to-day IT operational tasks while freeing up valuable time and resources. Meet service-level targets and business objectives with features designed to drive better business outcomes.

https://www.HPE.com/services/operational

HPE Lifecycle Services

HPE Lifecycle Services provide a variety of options to help maintain your HPE systems and solutions at all stages of the product lifecycle. A few popular examples include:

• – Lifecycle Install and Startup Services: Various levels for physical installation and power on, remote access setup, installation and startup, and enhanced installation services with the operating system.
• – HPE Firmware Update Analysis Service: Recommendations for firmware revision levels for selected HPE products, taking into account the relevant revision dependencies within your IT environment.
• – HPE Firmware Update Implementation Service: Implementation of firmware updates for selected HPE server, storage, and solution products, taking into account the relevant revision dependencies within your IT environment.
• – Implementation assistance services: Highly trained technical service specialists to assist you with a variety of activities, ranging from design, implementation, and platform deployment to consolidation, migration, project management, and onsite technical forums.
• – HPE Service Credits: Access to prepaid services for flexibility to choose from a variety of specialized service activities, including assessments, performance maintenance reviews, firmware management, professional services, and operational best practices.

Notes: To review the list of Lifecycle Services available for your product go to:

https://www.HPE.com/services/lifecycle

For a list of the most frequently purchased services using service credits, see the HPE Service Credits Menu

Supported NVIDIA GPUs and required Performance licenses per accelerator.