Inference Stack
The reference for how AI infrastructure actually fits together
Architectures
Catalog
Where it runs
About
Back to the interactive map
Silicon
Inferentia2
aws
AWS's cost-efficient, inference-only accelerator — 32 GB HBM, 190 TFLOPS FP16
Official docs
View in catalog
Used by
AWS Neuron SDK
Leads to
AWS Inf2 (Inferentia2)