Meta launches the biggest and best AI models it has ever built14m ago AMD puts 32,768 CPU cores in a rack built for AI agents32m ago Smug until weirdly silent: who told us to say “I am alive”?39m ago Anthropic's Claude AI submitted false murder tip to Philadelphia police39m ago How Anthropic’s Dynamic Workflows Coordinate Claude Agents43m ago Dell’s AI partner ecosystem adapts to Silicon Valley’s build-it-yourself buyers45m ago AWS Expands GPT-6 Access on Amazon Bedrock to Five Asia Pacific Regions49m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape52m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters53m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy55m ago Microsoft Research Introduces StudentSim for AI Tutor Training55m ago Why Big Tech Is Borrowing Billions to Fund AI Spending59m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy1h ago Meta Unveils New Series of Advanced A.I. Models2h ago

Meta launches the biggest and best AI models it has ever built14m ago AMD puts 32,768 CPU cores in a rack built for AI agents32m ago Smug until weirdly silent: who told us to say “I am alive”?39m ago Anthropic's Claude AI submitted false murder tip to Philadelphia police39m ago How Anthropic’s Dynamic Workflows Coordinate Claude Agents43m ago Dell’s AI partner ecosystem adapts to Silicon Valley’s build-it-yourself buyers45m ago AWS Expands GPT-6 Access on Amazon Bedrock to Five Asia Pacific Regions49m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape52m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters53m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy55m ago Microsoft Research Introduces StudentSim for AI Tutor Training55m ago Why Big Tech Is Borrowing Billions to Fund AI Spending59m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy1h ago Meta Unveils New Series of Advanced A.I. Models2h ago

Chips & Compute3 min reading time

AMD puts 32,768 CPU cores in a rack built for AI agents

The Next WebPublished 32 minutes ago

Read the full article

AMD unveiled Helion, an open rack design optimized for running AI agents with a CPU-only version featuring up to 32,768 cores. The design emphasizes power efficiency and will be available through partners starting November.

#amd #data-centers #energy-efficiency #helion #instinct-mi350p #venice #zen-6

More in Chips & Compute

Chips & Compute

Microsoft Prepares to Put Gigawatts of Its Chips in Data Centers

Covered by 6 sources6h ago

Chips & Compute11 min read

Run multi-node inference workloads using Ray LLM Deep Learning Containers

AWS Blog3h ago

Chips & Compute5 min read

ASUS Debuts XA P2N-E2 Server With Dual NVIDIA Vera CPUs at OCP

Unite.AI3h ago