Blog posts tagged "inference"

Previous articles walked through RDMA (Remote Direct Memory Access) as a programming model and InfiniBand as the fabric that was built around it. Both led to the same conclusion, even if it was never stated outright: moving data, not compute, becomes the bottleneck once systems scale. So what happens when you want RDMA, but you’re

Organizations everywhere are pushing AI and networks closer to the edge. With that expansion comes a challenge: how do you ensure reliable performance, efficiency, and security outside of the data center? Worker safety, healthcare automation, and the success of mobile private networks depend on a robust technology stack that can withstand

On October 23rd, we announced the beta availability of silicon-optimized AI models in Ubuntu. Developers can locally install DeepSeek R1 and Qwen 2.5 VL with a single command, benefiting from maximized hardware performance and automated dependency management. Application developers can access the local API of a quantized generative AI (Ge