AI Chips & Accelerators
AI chips are processors designed to accelerate model training and inference.
Follow GPUs, TPUs, custom accelerators, and high-bandwidth memory. Coverage compares architecture, performance, and availability for specific workloads.
Latest coverage
Articles
NewsNVIDIA says DSX boosted Lambda’s Blackwell throughput 24% within a fixed power budget
NewsTogether AI ports ThunderKittens kernels to NVIDIA Vera Rubin NVL72
Newsd-Matrix adopts NVIDIA NVLink Fusion for next-generation Raptor XPUs
NewsQualcomm and Amazon Agree to Develop Custom AI Chips for AWS
NewsNVIDIA Says Vera CPU Systems Are Shipping, With First Server Delivered to AWS
NewsOpenAI publishes first Jalapeño inference chip benchmarks
NewsSamsung approves record shareholder return of up to $79.6 billion on AI chip boom
NewsWaymo built a custom 5nm chip to process robotaxi sensor data
NewsNvidia readies a new export-compliant chip for China but disputes the 'LPU' label
NewsBroadcom seeks more than $60 billion in debt to fund AI chip access
NewsNvidia H200 chips reportedly reach China as ByteDance and Tencent get 10,000 each
NewsCerebras unveils CS-4 wafer-scale inference system, claiming up to 30x GPU speed