Adapted from gap analysis doc: https://docs.google.com/document/d/1Oz0rvy9BtTkB8FrQtamMlIMOiDrM2Ov5pUTZDzNtKXQ/edit?tab=t.0

Symphony can dispatch 10 tasks per core per second, Slurm can schedule and run 100s of jobs a second, we should improve the speed at which Kubernetes schedules hundreds of pods for jobs to boost overall job throughput.