AI Infrastructure
AI infrastructure is the compute, networking, and software used to train and serve models.
Follow training and inference stacks from cluster scheduling and networks to model serving. Coverage focuses on deployment, throughput, reliability, and operating cost.
Latest coverage
Articles
NewsAssemblyAI runs speech inference on EC2 Spot GPUs with queued retries
NewsMicrosoft winds down Oracle AI cloud capacity deal
NewsNVIDIA releases Dynamo deployment recipes for four Korean open models
NewsGoogle makes Agent Substrate 1.0 generally available on GKE
NewsAWS adds GPU partitioning to SageMaker Inference
NewsDatabricks plans AWS and Azure sovereign-cloud expansion in Europe
NewsSnowflake puts Cortex Training into public preview
NewsAWS adds India-only Kimi K3 inference profile to Bedrock
NewsMicrosoft puts Cobalt 200 VMs to work on chip design
NewsTogether AI launches self-tuning compiler for open-model inference
NewsAnthropic discloses $895.4 billion in compute commitments
NewsCohere commits more than C$4 billion to Canadian AI expansion