With the rise of agentic AI, the number of central processing units (CPUs) used within AI data centers is set to explode.
Production-scale testing on DeepInfra’s agent infrastructure showed the NVIDIA Vera CPU hosting up to 1.6x more concurrent AI ...
Nvidia is expanding its AI platform with its Vera CPU, a custom Arm-based server processor featuring its "Olympus" ...
Nvidia's new Vera CPU is strategically positioned to go after the $200 billion server CPU market, extending Nvidia's ...
Company also debuted the Qualcomm High Bandwidth Compute and the Qualcomm Dragonfly AI300 inference accelerator ...
The growth of AI inference workloads in data centers is boosting demand for server CPUs, a market that's dominated by AMD and Intel.
LiteRT.js runs machine learning models locally with CPU, GPU and emerging NPU acceleration, potentially reducing server infrastructure, inference charges and data movement.