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
NewsSGLang and Miles add day-zero support for Inkling 2 Mini
NewsVAST Data announces per-job storage controls for VAST AI OS 5.6
NewsAWS introduces cross-Region inference routing for SageMaker HyperPod
NewsAWS adds managed user administration to HyperPod Slurm clusters
NewsNscale says its first NVIDIA Vera Rubin NVL72 systems are online
NewsKioxia and Dell detail a single-rack object store with 157 PB of raw capacity
NewsAMD details automatic FlashInfer kernel routing on ROCm 10.1
NewsTogether AI launches Storage Accelerator for GPU clusters
NewsAWS adds distributed KV caching to ElastiCache for self-hosted LLMs
NewsNVIDIA updates DAQIRI for real-time scientific instruments
NewsAWS turns on continuous SageMaker inference monitoring by default
NewsNVIDIA and Microsoft expand AI stack across Azure, edge systems and Windows PCs
Videos
TechCrunch Disrupt 2026 · AIEEV
Oct 22, 2026
1:00:23Tech TalksFrom Prototype to Production: The Hidden Engineering of AI Inference
17:58Interview with Keerti Melkote: Anyscale Azure Integration and the Future of Ray
Dmytro Spodarets·Nov 24, 2025
53:04Dmytro Spodarets Podcast #1: AI Agents, Scalr, OpenTofu, DevOps tools, MLOps, LLMops
Dmytro Spodarets·Apr 15, 2025
1:02:32Accelerating Generative AI with HPE: From Development to Deployment
Dmytro Spodarets·Oct 28, 2024
50:18Exploring Infrastructure Management for GenAI Beyond Kubernetes
Dmytro Spodarets·Mar 15, 2024
55:03A Whirlwind Tour of ML Model Serving Strategies (Including LLMs)
Dmytro Spodarets·Jan 29, 2024
1:07:35Democratizing AI Deployment
Dmytro Spodarets·Dec 18, 2023
1:10:29Leveraging open-source LLMs for production
Dmytro Spodarets·Dec 4, 2023