Free AWS Virtual Training: Accelerating SLM Inference: Optimizing Small Language Models on AWS

Small Language Models (SLMs) offer compelling advantages for AI deployments, but building the optimal infrastructure can be challenging. This session explores deploying models like Llama and Mistral across AWS's silicon portfolio, including Graviton processors, NVIDIA GPUs, and AWS Inferentia and Trainium. Learn hardware selection strategies, optimization techniques, and deployment architectures that balance performance and cost-efficiency. Join us for practical guidance on matching your SLM workloads to the most appropriate AWS compute resources. Sign up today to join us virtually on August 20th at 10AM PT.