Benchmarking Llama 3.1 405B on 8 x AMD MI300X using vLLM and KubeAI

Blog: https://substratus.ai/blog/benchmarking-llama-3.1-405b-amd-mi300x Software used in video: vLLM for deploying LLMs: https://github.com/vllm-project/vllm KubeAI for deploying vLLM on K8s: https://github.com/substratusai/kubeai