Chapters
Executive summary
Hardware configuration
Software configuration
Deployment methodology
Executive summary
Hardware configuration
Software configuration
Deployment methodology
-
1Reference architecture Enterprise AI stack
-
2Infrastructure deployment
-
3Habana Kubernetes plugin deployment
-
4Running Gaudi® Jobs using Kubernetes
-
5Functional Validation with Optimum Habana
-
6Deploy and Serve models with Text Generation Inference (TGI)
-
7Deploy and Serve models with Virtual Large Language Models (vLLM)
-
8Deploy and Serve models with Parameter Efficient Fine-tuning