[2018 NIPS] Dynamic Space-Time Scheduling for GPU Inference
The authors evaluated different multiplexing (time & space) techniques for ML inferences on GPUs and proposed ideas to achieve the best tradeoff across criterias.
Almost all cloud inference service providers/frameworks assign each model an exclusive GPU. This, combined with the small batch sizes used in an online setting, results in low hardware utilization. Current approaches that multiplex workloads have different tradeoffs, and there is no single solution that wins on all criteria.
The authors proposed software-level fusion of kernel operators across multiple inference jobs to get the best of all worlds.