Data, AI, & Machine Learning
OpenAI Says Jalapeño Beats Nvidia Systems in Inference Tests
The custom chip delivered up to 1.9 times the peak throughput per watt and cut latency by as much as 72% in company tests.
The custom chip delivered up to 1.9 times the peak throughput per watt and cut latency by as much as 72% in company tests.
Series B brings Universal, Sony, Warner and EA onto its cap table as the Stable Diffusion maker pushes deeper into entertainment.
The M5 Ultra combines up to 512GB of unified memory with faster AI performance and support for clustering multiple systems.
The Nvidia systems will power the first 30 MW of an AI computing facility in Hyderabad, with delivery scheduled for early 2027.
The BLAZO i-TRK automatically adjusts its driving mode to road gradients and payload, while Mahindra claims up to 10% better fuel efficiency.