12 articles
Hugging Face’s Reef discussion points to a new agent architecture where inference infrastructure collects feedback and improves behavior continuously.
AI inference growth is shifting the hardware bottleneck from training throughput toward memory bandwidth, capacity, networking, and power efficiency.
Jev says its decision engine can cut AI decision costs by 100x, putting routing, caching, and latency—not just model quality—at the center of inference economics.
AMD's FastFlowLM announcement suggests the company wants to make local and edge inference a real part of the AI economics conversation.
Cisco's 2026 WAN report frames agentic AI and inference traffic as a long-term networking design problem.
Groq is reportedly raising 650 million dollars as AI infrastructure shifts from training chips to inference clouds.
XCENA raised $135 million as investors focus on memory bandwidth, not only compute, as the next constraint for AI inference.
Cerebras priced its IPO above range, testing public investor appetite for wafer-scale AI chips and inference infrastructure.
Panthalassa raised $140 million to build wave-powered AI inference nodes at sea, a sign of how far the compute bottleneck is pushing infrastructure.
Huawei's expected AI chip gains in China show how export controls are pushing inference hardware, software, and sovereignty together.
NVIDIA unveils its most powerful architecture yet, Vera Rubin, designed to facilitate the next generation of agentic AI and power global-scale AI factories.
What happens when 'cheap tokens' add up to massive enterprise costs. Learn how to build an Inference Router to dynamically switch between cloud and local models.