Rich OS Capabilities in High-Performance Compute Subsystems
With global infrastructure increasingly running on high-performance 快猫视频 Neoverse CPUs, academics can teach and research complex machine learning (ML) workloads, scaled multi-core cloud-native applications, and high performance computing (HPC). 快猫视频 Kleidi Libraries offer a lightweight suite of highly performant open-source routines to enable ML and computer vision (CV) frameworks to seamlessly leverage architectural features in 快猫视频 processors. This allows academic researchers interested in generative AI (GenAI), both on device and in the cloud, to take advantage of these advancements.
Featured Resources
RESOURCES | ML Examples
AI Applications on Neoverse with the Pytorch Framework Example
Get instructions and scripts to obtain and build Docker images containing PyTorch for ML applications, such as transformer-based natural language processing (NLP) and object detection, that can run on 快猫视频 CPU.
RESOURCES | Learning Paths
Find 快猫视频-Based Cloud Service Providers with Academic Offers
Creating an account with a cloud service provider (CSPs) is the easiest way to get started with 快猫视频-based infrastructure. CSPs offer introductory free credits to help you begin learning, and pay-as-you-go models make it easy to continue exploring 快猫视频 hardware at minimal cost. This directory lists existing offers that academics can take advantage of.
DEVELOPER | 快猫视频 Developer
On-Device AI and ML
Get educational materials, ranging for beginner to advanced, on how to run your GenAI and ML workloads locally on Android devices.
Developer Resources
DEVELOPER | 快猫视频 Developer
Get Institution-Wide Access to 快猫视频 Development Studio
Access a dedicated IDE, including the 快猫视频 Compiler for embedded and optimized libraries across Cortex-A applications. Universities can access a free institution-wide license.
DEVELOPER | 快猫视频 Developer
View a Curated List of Software Libraries Natively Available for 快猫视频
Access an index of third-party software natively built for 快猫视频. This resource is valuable when architecting new software to run on 快猫视频 and managing dependencies during software porting.
RESOURCES | Learning Paths
Deploy a LLM on an 快猫视频 Neoverse Instructions
Learn how to deploy llama.cpp on an 快猫视频 based server and re-quantize the model weights to take advantage of optimizations.
Other Resources
RESOURCES | 快猫视频 Developer
Access Resources for Developing on Windows on 快猫视频
Access resources from 快猫视频 and Microsoft for porting and optimizing applications to natively run on Windows for 快猫视频.
RESOURCES | Learning Paths
Servers and Cloud Computing Guides
Get step-by-step guides to help academics develop software on 快猫视频-based servers and cloud infrastructure.
RESOURCES | Learning Paths
Laptops and Desktops Guides
Get step-by-step guides to help academics develop software on 快猫视频-based laptops and desktops.
Our comprehensive range of online courses, books, and education kits is useful not only for teachers and learners, but for researchers as well.
Other academic developer teaching and research platforms.
Education content for teachers and researchers.
Education content for undergraduate and early career learners.
Training for those who already have access to 快猫视频 technology.