FSD-Inference: Fully Serverless Distributed Inference with Scalable Cloud Communication

arXiv:2403.15195v1 Announce Type: cross
Abstract: Serverless computing offers attractive scalability, elasticity and cost-effectiveness. However, constraints on memory, CPU and function runtime have hindered its adoption for data-intensive applications and machine learning (ML) workloads. Traditional 'server-ful' platforms enable distributed computation via fast networks and well-established inter-process communication (IPC) mechanisms such as MPI and shared memory. In the absence of such solutions in the serverless domain, parallel computation with significant IPC requirements is challenging. We present FSD-Inference, the first fully serverless and …

abstract adoption applications arxiv cloud communication computation computing constraints cost cpu cs.ai cs.dc cs.lg data distributed elasticity fsd function however inference machine machine learning memory mpi networks platforms process scalability scalable server serverless serverless computing type via workloads