Skip to content

fastmachinelearning/SuperSONIC

Repository files navigation

ci [CMS] docs helm lint helm docs

SuperSONIC

The SuperSONIC project implements common server infrastructure for GPU inference-as-a-service to accelerate machine learining algorithms at large high energy physics (HEP) and multi-messenger astrophysics (MMA) experiments. The server infrastructure is designed for deployment at Kubernetes clusters equipped with GPUs.

The main components of SuperSONIC are:

  • Nvidia Triton inference servers
  • Dynamic muti-purpose Envoy Proxy:
    • Load balancing
    • GPU saturation prevention
    • Token-based authentication (optional)
  • Load-based autoscaling via KEDA

Documentation

Server diagram

diagram

Status of deployment

CMS ATLAS IceCube
Geddes cluster (Purdue) - -
Nautilus cluster (NRP)

About

Common SONIC server infrastructure for HEP and MMA experiments

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published