Developers use Machine Learning (ML) platforms to train ML models and then deploy these ML models as web services for inference (prediction). A key challenge for platform providers is to guarantee response-time Service Level Agreements (SLAs) for inference workloads while maximizing resource e�ciency. Swayam is a fully distributed autoscaling framework that exploits characteristics of production ML inference workloads to deliver on the dual challenge of resource e�ciency and SLA compliance. Our key contributions are (1) model-based autoscaling that takes into account SLAs and ML inference workload characteristics, (2) a distributed protocol that uses partial load information and prediction at frontends to provision new service instances, and (3) a backend self-decommissioning protocol for service instances. We evaluate Swayam on 15 popular services that were hosted on a productionML-as-a-service platform, for the following service-speci�c SLAs: for each service, at least 99% of requests must complete within the response-time threshold. Compared to a clairvoyant autoscaler that always satis�es the SLAs (i.e., even if there is a burst in the request rates), Swayam decreases resource utilization by up to 27%, while meeting the service-speci�c SLAs over 96% of the time during a three hour window. Microsoft Azure’s Swayam-based framework was deployed in 2016 and has hosted over 100,000 services.