Archives mensuelles : juin 2026

Running the AI Factory: How Enterprises Operationalize AI Placement at Scale

Part 3 of our CPU:GPU blog series now moves from metaphor to operations.

Publié dans Non classé | Commentaires fermés sur Running the AI Factory: How Enterprises Operationalize AI Placement at Scale

Intel® Xeon® 6 Processors: The Ultimate Host CPU Solution for AI-Accelerated Systems and Agentic AI

When it comes to choosing the right foundation for your AI infrastructure, Intel Xeon 6 processors stand out as the clear winner.

Publié dans Non classé | Commentaires fermés sur Intel® Xeon® 6 Processors: The Ultimate Host CPU Solution for AI-Accelerated Systems and Agentic AI

Agentic Code Execution: A Leaner Way to Build AI Agents with Open Models

The landscape of AI agents is shifting from simple « ask-and-receive » interactions toward complex, multi-step reasoning.

Publié dans Non classé | Commentaires fermés sur Agentic Code Execution: A Leaner Way to Build AI Agents with Open Models

CPU Overload Despite Having iGPU: Here’s Why?

CPU overload with unused iGPU? You’re leaving performance on the table.Learn how to offload video decoding, preprocessing, and AI inference to Intel® iGPU using DL Streamer—and unlock real-time analytics with lower power and higher efficiency.

Publié dans Non classé | Commentaires fermés sur CPU Overload Despite Having iGPU: Here’s Why?

Lablup adds Intel Arc Pro B70 support to Backend.AI

Building on its existing support for Intel Gaudi 2/3 AI accelerators, Backend.AI now extends its Intel lineup to Arc graphics, starting with the Arc Pro B70. With a larger memory pool than competing desktop-grade options, the B70 shows its clearest … Continuer la lecture

Publié dans Non classé | Commentaires fermés sur Lablup adds Intel Arc Pro B70 support to Backend.AI

Unlock Cost-Effective Enterprise AI with Lenovo ThinkSystem SR650 V4 with Intel® Xeon® 6 CPUs

We explore the scalability and performance of agentic document summarization running on a Red Hat OpenShift cluster built on Lenovo ThinkSystem SR650 V4 servers powered by Intel Xeon 6 processors.

Publié dans Non classé | Commentaires fermés sur Unlock Cost-Effective Enterprise AI with Lenovo ThinkSystem SR650 V4 with Intel® Xeon® 6 CPUs

Trust in the Age of Sovereign AI with Intel, Nvidia, and Red Hat

Confidential Computing is emerging as a foundational technology for Sovereign AI.

Publié dans Non classé | Commentaires fermés sur Trust in the Age of Sovereign AI with Intel, Nvidia, and Red Hat

Unleash the Power of Intel® Xeon® 6 Processors with P-cores as AI Host CPU with Priority Core Turbo

By enabling priority cores to exceed standard all-core turbo limits and approach higher turbo frequency levels, PCT accelerates essential operations, reduces processing delays, and improves overall system responsiveness.

Publié dans Non classé | Commentaires fermés sur Unleash the Power of Intel® Xeon® 6 Processors with P-cores as AI Host CPU with Priority Core Turbo

Speed-up JAX LLM Training on Intel® Xeon® 6 CPU: Activation Offloading on Heterogeneous Systems

JAX-based Activation Offloading on Intel® Xeon® 6 with P-cores systems offers an effective alternative to activation recomputation, repurposing the CPU’s large DDR5 host memory as a live activation store and leveraging XLA’s asynchronous compute–communication overlap to avoid throughput loss.

Publié dans Non classé | Commentaires fermés sur Speed-up JAX LLM Training on Intel® Xeon® 6 CPU: Activation Offloading on Heterogeneous Systems

Intel® Xeon® 6 Processors and Intel® AMX Deliver More Concurrent Users with NVIDIA HGX B200 Systems

This blog introduces a heterogeneous architecture that co-runs vLLMs on both CPUs and GPUs to improve overall system efficiency.

Publié dans Non classé | Commentaires fermés sur Intel® Xeon® 6 Processors and Intel® AMX Deliver More Concurrent Users with NVIDIA HGX B200 Systems