Technology ❯ Artificial Intelligence ❯ Hardware

Processors

Tensor Processing Units AI Chips Nvidia Custom Chips AMD AI Accelerators Nvidia H200 ASICs Graphics Processors CPU AI Processors Wafer-Scale Processors OpenAI AI Accelerator Chips TPUs Jalapeño Nvidia RTX Spark Intelligence Processors In-house Design Geotracking Chipmakers Central Processing Units Custom AI Chips Nvidia H20 Custom Processors Huawei Ascend Cerebras CS-4 Wafer Scale Engine Market Impact Domestic Chips Broadcom M4 Chip Market Trends Cerebras Systems Wafer-Scale Engine Intel Processors Manufacturers Zhenwu NVIDIA Vera CPU

OpenAI’s Jalapeño Chip Claims Major Inference Efficiency and Latency Gains

OpenAI’s InferenceX benchmarks claim the Broadcom‑co‑developed ASIC delivers higher throughput, lower latency, better energy efficiency for interactive AI workloads.

Stories older than 24h

Cerebras Unveils CS-4 Rack With 30x Inference Claim as Stock Slides After Q2 Results

China Poised to Let Select Tech Firms Buy Limited Nvidia H200 Chips

Alibaba Activates 10,000-Chip AI Cluster in China Telecom Data Center

Google Sets Ironwood TPU v7 for General Availability With Axion CPUs in Cloud