{"id":24493021,"url":"https://github.com/fastmachinelearning/supersonic","last_synced_at":"2025-04-14T01:40:36.685Z","repository":{"id":260693557,"uuid":"876768230","full_name":"fastmachinelearning/SuperSONIC","owner":"fastmachinelearning","description":"Server infrastructure for GPU inference-as-a-service in large scientific experiments","archived":false,"fork":false,"pushed_at":"2025-03-14T16:30:50.000Z","size":9263,"stargazers_count":5,"open_issues_count":0,"forks_count":5,"subscribers_count":15,"default_branch":"main","last_synced_at":"2025-04-12T22:18:18.181Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://fastmachinelearning.org/SuperSONIC/","language":"JSON","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fastmachinelearning.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-10-22T14:22:41.000Z","updated_at":"2025-03-15T16:45:08.000Z","dependencies_parsed_at":"2024-11-01T22:19:05.223Z","dependency_job_id":"e308279f-3479-4dcc-bbfc-9d6d9f005935","html_url":"https://github.com/fastmachinelearning/SuperSONIC","commit_stats":null,"previous_names":["fastmachinelearning/supersonic"],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2FSuperSONIC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2FSuperSONIC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2FSuperSONIC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fastmachinelearning%2FSuperSONIC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fastmachinelearning","download_url":"https://codeload.github.com/fastmachinelearning/SuperSONIC/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248809039,"owners_count":21164893,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-01-21T19:18:54.563Z","updated_at":"2025-04-14T01:40:36.668Z","avatar_url":"https://github.com/fastmachinelearning.png","language":"JSON","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Version](https://img.shields.io/github/v/release/fastmachinelearning/SuperSONIC)\n[![DOI](https://zenodo.org/badge/876768230.svg)](https://doi.org/10.5281/zenodo.14815348)\n[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/supersonic)](https://artifacthub.io/packages/search?repo=supersonic)\n![Downloads](https://img.shields.io/github/downloads/fastmachinelearning/SuperSONIC/total)\n![License](https://img.shields.io/github/license/fastmachinelearning/SuperSONIC)\n\n\u003ch1\u003e\n\u003cspan style=\"margin: -10px -10px -10px -5px\"\u003e\n  \u003cimg src=\"./docs/img/SuperSONIC_small_light_128.png#gh-dark-mode-only\" alt=\"logo\" height=\"40\"\u003e\n  \u003cimg src=\"./docs/img/SuperSONIC_small_128.png#gh-light-mode-only\" alt=\"logo\" height=\"40\"\u003e\n\u003c/span\u003e\n   SuperSONIC\n\u003c/h1\u003e\n\nThe [SuperSONIC](http://fastmachinelearning.org/SuperSONIC/ \"SuperSONIC\") project implements server infrastructure for **inference-as-a-service**\napplications in large high energy physics (HEP) and multi-messenger astrophysics\n(MMA) experiments. The server infrastructure is designed for deployment at [Kubernetes](https://kubernetes.io) clusters equipped with GPUs.\n\nThe main components of SuperSONIC are:\n- [Nvidia Triton](https://developer.nvidia.com/triton-inference-server) inference servers\n- Dynamic muti-purpose [Envoy Proxy](envoyproxy.io):\n  - Load balancing\n  - Rate limiting\n  - GPU saturation prevention\n  - Token-based authentication\n- (optional) Load-based autoscaling via [KEDA](keda.sh)\n- (optional) [Prometheus](https://prometheus.io) instance (deploy custom or connect to existing)\n- (optional) Pre-configured [Grafana](https://grafana.com) dashboard\n- (optional) [OpenTelemetry Collector](https://opentelemetry.io/docs/collector/) and [Grafana Tempo](https://grafana.com/docs/tempo/latest/) for advanced monitoring.\n\n\n## Installation\n\nThe installation is done via a custom Helm plugin which takes care of\ninternal connectivity of the chart components. Standard Helm installation\nis also supported, but requires a lot more manual configuration.\n\n```\nhelm plugin install https://github.com/fastmachinelearning/SuperSONIC/\nhelm install-supersonic \u003crelease-name\u003e -n \u003cnamespace\u003e -f \u003cyour-values.yaml\u003e\n```\n\nInstaller plugin usage:\n```\nUsage:\n  helm install-supersonic [RELEASE_NAME] [flags]\n\nFlags:\n  -h, --help              Show this help message\n  -f, --values            Specify values file for custom configuration\n  -n, --namespace         Specify Kubernetes namespace for deployment\n  --version               Specify chart version (default: latest version)\n                          Note: Ignored if --local flag is set\n  --local                 Install from local chart path instead of remote repository\n  --path                  Local chart path (default: ./helm/supersonic)\n                          Only used when --local flag is set\nAdditional flags will be passed directly to the 'helm install' command\n```\n\nTo construct the `values.yaml` file for your application, follow [Configuration guide](http://fastmachinelearning.org/SuperSONIC/configuration-guide.html \"Configuration guide\").\n\nThe full list of configuration parameters is available in the [Configuration reference](http://fastmachinelearning.org/SuperSONIC/configuration-reference.html \"Configuration reference\").\n\n\n## Server diagram\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/fastmachinelearning/SuperSONIC/blob/main/docs/img/diagram.svg#gh-light-mode-only\" alt=\"diagram\" width=\"700\"/\u003e\n  \u003cimg src=\"https://github.com/fastmachinelearning/SuperSONIC/blob/main/docs/img/diagram-dark.svg#gh-dark-mode-only\" alt=\"diagram-dark\" width=\"700\"/\u003e\n\u003c/p\u003e\n\n## Grafana dashboard\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/fastmachinelearning/SuperSONIC/blob/main/docs/img/grafana.png\" alt=\"grafana\" width=\"700\"/\u003e\n\u003c/p\u003e\n\n## Status of deployment\n\n|  | **[CMS](https://home.cern/science/experiments/cms)**      | **[ATLAS](https://home.cern/science/experiments/atlas)**    | **[IceCube](https://icecube.wisc.edu)**  |\n|:---|:---:|:---:|:---:|\n| **[Purdue Geddes](https://www.rcac.purdue.edu/compute/geddes)**   | ✅ | - | - |\n| **[Purdue Anvil](https://www.rcac.purdue.edu/compute/anvil)**   | ✅ | - | - |\n| **[NRP Nautilus](https://docs.nationalresearchplatform.org)**    | ✅  |  ✅ |   ✅   |\n| **[UChicago](https://af.uchicago.edu/)**    |  -  |  ✅ |   -   |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffastmachinelearning%2Fsupersonic","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffastmachinelearning%2Fsupersonic","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffastmachinelearning%2Fsupersonic/lists"}