Canonical announced the beta release of optimized inference snaps, a new way to deploy AI models on Ubuntu devices, with automatic selection of optimized engines, quantizations and architectures based on the specific silicon of the device. Canonical is working with a wide range of silicon providers to deliver their optimizations of well-known LLMs to the developers and devices.
Canonical announced the beta release of optimized inference snaps, a new way to deploy AI models on Ubuntu devices, with automatic selection of optimized engines, quantizations and architectures based on the specific silicon of the device. Canonical is working with a wide range of silicon providers to deliver their optimizations of well-known LLMs to the developers and devices.
Ampere® and ZMicro have joined forces to bring cutting edge computing to rugged and deployable servers. Shielding Ampere’s® Altra® family of processors is ZMicro’s aluminum and carbon fiber chassis capable of operating in the harshest of deployed environments.
512 Core Petabyte Carry-On Computer for Edge AI Powered by Ampere – The Nexus with Ampere is a carry-on designed to bring purpose-built computing solutions anywhere you need to be. Whether you need to do on-site cyber security assessment, or you want to accelerate your network capabilities with edge computing, the Nexus offers a rugged travel-ready package with the professional computing power you need.
The Nucleus 1U with Ampere processors is a compact, short-depth 1U server with substantial NVMe storage and NVIDIA GPU support. It is primarily designed to deliver high-density, high-throughput, and energy-efficient performance for cloud-native and AI inference workloads in space- and power-constrained environments like Edge, Telco/5G and on-premises.
The Intelligent Video Recording (IVR) solution is engineered for unparalleled video stream density and exceptional power efficiency. This state-of-the-art computer vision platform leverages Ampere® high performance server class processors with DEEPX ultra-efficient AI inference chips. Various configuration options for CPU and AI inference processors allows customers to deploy this solution from space- and power-constrained edge deployments to camera-dense, large-scale sites.
View AI can support over 250 users on a single AmpereOne M server. The AI assistant provides an end-to-end solution that transforms raw data into AI-ready assets with built-in, deployable conversational experiences, helping enterprises gain valuable insights from their data while maintaining data sovereignty and compliance.
Iterate.AI’s genAI platform Generate boosts enterprise productivity by delivering meaningful insights or outcomes in minutes. Powered by Ampere processors, this powerful platform can be deployed without requiring costly hardware accelerators or exotic cooling solutions.
Wallaroo’s breakthrough platform facilitates the last mile of the machine learning journey – getting ML into your production environment and monitoring ongoing performance – with incredible speed, scale, and efficiency. Companies across all industries including retail, finance, manufacturing, and healthcare are turning to Wallaroo to easily deploy and manage ML models at scale.
Wallaroo’s Universal AI Inference Platform optimized for Ampere® processors redefines how enterprises deploy, manage, and monitor AI workloads leading to efficient, cost effective applications that drive maximum business impact and ROI at factory scale.
Partner with us as we build an ecosystem of leading AI solutions powered by industry-leading cloud native technologies.
"*" indicates required fields