Ai Inference
The latest Ai Inference coverage — news, analysis, and updates from the WindowsNews.AI desk.
Azure Taps AMD's Helios AI Racks to Ease Compute Crunch, but Capacity Details Remain Scarce
Microsoft committed to a large-scale deployment of AMD’s Helios rack-scale artificial intelligence infrastructure, giving Azure’s own services and its paying cloud customers access to...
AMD’s New PCIe Card Puts 144GB of HBM3E Within Reach of Conventional Servers
AMD has started showing off the Instinct MI350P, a PCIe 5.0 accelerator card that packs 144GB of high-bandwidth HBM3E memory, at multiple industry events this summer. The card brings server-grade AI...
New Chip Packaging from AMD and Qualcomm Aims to Eliminate AI’s Memory Hurdle
In the space of two weeks, AMD and Qualcomm separately unveiled new processor architectures that tackle a persistent obstacle in artificial intelligence: the memory bottleneck. AMD integrated LPDDR5X...
OpenAI Slashes AI Inference Costs by Over 50% with New Software Breakthrough
OpenAI engineers have reportedly developed a software optimization that cuts the inference cost of existing AI models by more than half, a move that could dramatically alter the economics of...
AWS G7 Instances with NVIDIA Blackwell GPUs Bring Enterprise AI to Windows Workloads
Amazon Web Services has officially launched the Amazon EC2 G7 instance family, packing NVIDIA’s latest RTX PRO 4500 Blackwell Server Edition GPUs alongside Intel Xeon 6 processors, and making them...
Microsoft Maia 200 Deal With Anthropic Could Halve Azure AI Token Costs
Microsoft is in talks to supply Anthropic with its custom Maia 200 AI accelerators, a move that could dramatically cut the cost of running large-scale AI models on Azure while challenging NVIDIA’s...
Anthropic in talks to run Claude on Microsoft's custom Maia 200 AI chip
Anthropic is reportedly in early discussions with Microsoft to deploy its Claude large language models on Azure cloud servers equipped with Microsoft’s custom Maia 200 AI accelerator. The move, if...
Microsoft Azure Maia 200 AI Accelerator: Breaking Moore's Law Limits with Custom Silicon
Microsoft's Azure Maia 200 AI accelerator represents a fundamental shift in how the company approaches artificial intelligence compute, moving beyond traditional GPU architectures to custom silicon...
Intel's Bartlett Lake and Panther Lake Processors: AI-Powered Edge Computing for Windows Systems
Intel has quietly expanded its client and embedded processor portfolio with two targeted families—Core Series 2 \"Bartlett Lake\" and \"Panther Lake\"—specifically designed for edge computing...
Microsoft Silently Upgrades Windows 11 AI Muscles for RTX PCs with KB5079257
Microsoft just made your RTX-powered Windows 11 PC better at running AI—without any fanfare. Through a quiet Windows Update component called KB5079257, the company is pushing version 1.8.24.0 of...
NVIDIA 532.03 Driver: GTX 1650 Support & AI Inference Boost Explained
NVIDIA's GeForce Game Ready Driver 532.03 represents a significant update that bridges the gap between older mainstream hardware and modern AI capabilities, particularly benefiting owners of the...
Intel OpenVINO KB5077525 Update: AI Performance Boost for Windows 11 Explained
Microsoft's KB5077525 update, delivering Intel OpenVINO Execution Provider version 1.8.63.0, represents a significant advancement in AI inference capabilities for Windows 11 systems. This optional...