Inference Stack
The reference for how AI infrastructure actually fits together
Architectures
Catalog
Where it runs
About
Back to the interactive map
Cloud Instances
Azure ND MI300X v5
azure
Azure ND MI300X v5 — 8× AMD MI300X, 192 GB HBM3 per GPU, InfiniBand NDR 400 Gbps
Official docs
Used by
MI300X