AMD EPYC and VMware vSphere AI-in-a-Box Build Guide (58765) - This user guide describes how to deploy Large Language Models (LLMs) on AMD EPYC and vSphere using serverspowered by 4th Gen AMD EPYC processors. It focuses on deploying Llama2 models for multi-user requests, specificallytargeting LLMs such as llama-2-7b-chat-hf and its variant models by including detailed, step-by-step instructions forestablishing a VMware multi-node cluster environment, creating Ubuntu VM, installing docker and deploying LLama2.