| Mobile Web

Search results for vLLM

AI & Enterprise

Red Hat expands cooperation with Nvidia to strengthen agentic AI security capabilities

Red Hat said on Wednesday it is expanding cooperation with Nvidia and will work to spread security-enabled, enterprise-grade agentic AI across open hybrid clouds through Red Hat AI Factory with NVIDIA. The company said it is developing the OpenShell Reference Architecture with Nvidia to secure safety and control at the core of enterprise agentic AI deployments. It said the architecture combines access control, an AI gateway and high-performance inference with Nvidia technologies.

AI & Enterprise

Google open-sources TorchTPU to help move PyTorch apps to TPUs

Google has released an open-source project called TorchTPU designed to help developers move PyTorch-based AI applications to its TPU chips and Google Cloud. The tool aims to run existing PyTorch apps on TPUs without rewriting code, requiring only simple configuration changes. TechCrunch also noted Amazon has launched TorchNeuron for moving PyTorch apps to its Trainium chips and AWS, while submitting code to decouple features from Nvidia chips.

Industry

Rebellions to supply large volumes of homegrown NPUs for public CCTV control

A South Korean neural processing unit (NPU) will be deployed for the first time at a public safety infrastructure site. AI chip company Rebellions said on Aug. 3 it won server infrastructure contracts for Gyeongsangnam-do Provincial Government and Ulsan Metropolitan City CCTV control centres under a public AI CCTV conversion project led by the Ministry of Science and ICT and the National Information Society Agency. It plans to deliver its server-type NPU, ATOM-Max, from August.