Inference performance of Llama 3.1 8B using vLLM across various GPUs and CPUs

Introduction Following our previous evaluation of Llama 3.1 8B inference performance on Azure’s ND-H100-v5 infrastructure using vLLM, this report broadens the scope to compare inference performance across a range of GPU and CPU platforms. Using the Hugging Face inference benchmarker, we assess not only throughput and latency but also the…