{"id":19329756,"url":"https://github.com/outerbounds/triton-metaflow-starter-pack","last_synced_at":"2025-07-06T22:07:51.223Z","repository":{"id":207770246,"uuid":"719309421","full_name":"outerbounds/triton-metaflow-starter-pack","owner":"outerbounds","description":null,"archived":false,"fork":false,"pushed_at":"2023-11-18T15:24:49.000Z","size":4355,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-04-12T18:29:41.733Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/outerbounds.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-15T22:29:42.000Z","updated_at":"2024-05-03T14:32:50.000Z","dependencies_parsed_at":"2024-11-10T02:29:51.426Z","dependency_job_id":"7a1ff256-8efc-49ce-a826-7b8378a8186d","html_url":"https://github.com/outerbounds/triton-metaflow-starter-pack","commit_stats":null,"previous_names":["outerbounds/triton-metaflow-starter-pack"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/outerbounds/triton-metaflow-starter-pack","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/outerbounds%2Ftriton-metaflow-starter-pack","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/outerbounds%2Ftriton-metaflow-starter-pack/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/outerbounds%2Ftriton-metaflow-starter-pack/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/outerbounds%2Ftriton-metaflow-starter-pack/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/outerbounds","download_url":"https://codeload.github.com/outerbounds/triton-metaflow-starter-pack/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/outerbounds%2Ftriton-metaflow-starter-pack/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263980181,"owners_count":23538922,"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":"2024-11-10T02:29:47.562Z","updated_at":"2025-07-06T22:07:51.202Z","avatar_url":"https://github.com/outerbounds.png","language":"Python","funding_links":[],"categories":["Examples \u0026 Tutorials"],"sub_categories":[],"readme":"\u003ctable\u003e\n    \u003ctr\u003e\u003cimg style=\"display: block; float: center; max-width: 80%; height: auto; margin: auto; float: none!important;\" src=\"img/metaflow-triton.png\"/\u003e\u003c/tr\u003e \n    \u003ctr\u003e\n        \u003ctd style=\"padding-top: 100px\"\u003e \u003cimg src=\"img/lineage.png\"/\u003e\n        \u003ctd style=\"padding-top: 100px\"\u003e \u003cimg src=\"img/server-arch.png\"/\u003e \n    \u003c/tr\u003e\n\u003c/table\u003e\n\n# What is this repo\n\nThis code will help you get started using NVIDIA's [Triton Inference Server](https://developer.nvidia.com/triton-inference-server) and [Outerbounds](https://outerbounds.com/platform) (built on open-source [Metaflow](https://docs.metaflow.org/)).\n\n# How to use this repo\n\nThere are subdirectories each containing different getting started toolkits for using Triton with Outerbounds. You can find detailed instructions in the README files in each subdirectory.\n- The [trees](./trees) repository provides a template for how to use Metaflow to orchestrate training and tuning of Scikit-learn, XGBoost, or LightGBM models, pushing the resulting model to cloud storage so it is ready to be used on a Triton Inference Server.\n- The [llm](./llm) repository provides a template for how to use Metaflow to orchestrate fine-tuning for transformer models, pushing the resulting model and tokenizer state to cloud storage so it is ready to be used on a Triton Inference Server.\n\n# What you need to get the most out of it\n- Set up an inference server where you want to host models.\n    - Best to have a GPU for `/llm` \n- Access to a [Metaflow deployment](https://outerbounds.com/engineering/welcome/)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fouterbounds%2Ftriton-metaflow-starter-pack","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fouterbounds%2Ftriton-metaflow-starter-pack","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fouterbounds%2Ftriton-metaflow-starter-pack/lists"}