5 articles tagged
CPU-based autoscaling scales GPU inference too late. A 2026 config guide to HPA, KEDA, external metrics and Karpenter, with YAML for queue-depth and scale-to-zero scaling of LLM inference on Kubernetes.
AWS shipped two NVIDIA Blackwell inference families in 2026: G7 with up to 4.6x the inference of G6, and G7e that runs a 70B model on a single 96 GB GPU and is now live in Mumbai. Here is the spec, cost and decision
AWS Trainium3 is generally available in 2026 with 30-40% better price-performance than Trainium2. Here is how it compares with NVIDIA H200 and B200 on real cost per token and what Neuron migration costs.
A specs-and-cost comparison of Google Ironwood (TPU7x) and NVIDIA B200 for AI inference in 2026: memory, bandwidth, scale, software lock-in, consumption models, and a decision matrix for when to pick each.
Apple extended Private Cloud Compute to Nvidia Blackwell GPUs in Google Cloud to run AFM 3 Cloud Pro, its ~1.2T-parameter server model. Here are 5 architecture decisions behind it, for private-cloud AI teams.
