📄️ Llama-2 on Inferentia
Note: Use of this Llama-2 model is governed by the Meta license.
📄️ Mistral-7B on Inferentia2
Note: Mistral-7B-Instruct-v0.2 is a gated model in Huggingface repository. In order to use this model, one needs to use a HuggingFace Token.
📄️ Stable Diffusion on Inferentia
This example blueprint deploys a stable-diffusion-xl-base-1-0 model on Inferentia2 instance running as a worker node in an EKS cluster. The model is served using RayServe.
📄️ Stable Diffusion on GPU
We are actively enhancing this blueprint to incorporate improvements in observability and logging.