New ‘Test-Time Training’ method lets AI keep learning without exploding inference costs

By allowing models to actively update their weights during inference, Test-Time Training (TTT) creates a "compressed memory" ...
Business Wire

Gcore Unveils Inference at the Edge – Bringing AI Applications Closer to End Users for Seamless Real-Time Performance

LUXEMBOURG--(BUSINESS WIRE)--Gcore, the global edge AI, cloud, network, and security solutions provider, today announced the launch of Gcore Inference at the Edge, a breakthrough solution that ...
InfoQ

OpenAI Presents Research on Inference-Time Compute to Better AI Security

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...
Forbes

IBM Targets Enterprise AI Advantage With Faster Inference As Rivals Chase Bigger Models

Forbes contributors publish independent expert analyses and insights. Victor Dey is an analyst and writer covering AI and emerging tech. As OpenAI, Google, and other tech giants chase ever-larger ...
Forbes

The Inference Economy: How Sparse Computing And Model Optimization Are Reshaping Enterprise AI Deployment

The AI industry stands at an inflection point. While the previous era pursued larger models—GPT-3's 175 billion parameters to PaLM's 540 billion—focus has shifted toward efficiency and economic ...
Business Wire

MosaicML Launches Inference API and Foundation Series for Generative AI; Leading Open Source GPT Models, Enterprise-Grade Privacy and 15x Cost Savings

SAN FRANCISCO--(BUSINESS WIRE)--Today, MosaicML, the leading Generative AI infrastructure provider, announced MosaicML Inference and its foundation series of models for enterprises to build on. This ...
insideHPC

Cerebras Reports 3,000 Tokens Per Second Inference on OpenAI gpt-oss-120b Model

SUNNYVALE, Calif. & SAN FRANCISCO — Cerebras Systems today announced inference support for gpt-oss-120B, OpenAI’s first open-weight reasoning model, running at record inference speeds of 3,000 tokens ...