During November 2024, this developer contributed to the awslabs/fmbench-orchestrator repository by building a configuration-driven benchmarking workflow for CPU-based evaluation of the Llama 3.2 1B model. Leveraging AWS, YAML, and cloud computing skills, they enabled scalable and reproducible CPU benchmarks across AWS EC2 instances. Their work introduced configuration files that map CPU-optimized EC2 hardware, allowing for orchestrated performance testing and easier onboarding of new models. The developer also drafted setup documentation and usage notes to facilitate adoption across teams. While the contribution focused on a single feature, it established a solid foundation for future cross-hardware benchmarking and evaluation efforts.