Inference Stack
The reference for how AI infrastructure actually fits together
Architectures
Catalog
Where it runs
About
Back to the interactive map
Silicon
Trainium2
aws
AWS's 2nd-gen custom training/inference accelerator — 96 GB HBM3e, 667 TFLOPS BF16, AWS-exclusive
Official docs
View in catalog
Used by
AWS Neuron SDK
Leads to
AWS Trn2 (Trainium2)