{"id":13781142,"url":"https://oracle.github.io/graphpipe/","last_synced_at":"2025-05-11T14:34:51.321Z","repository":{"id":57435864,"uuid":"138919118","full_name":"oracle/graphpipe","owner":"oracle","description":"Machine Learning Model Deployment Made Simple","archived":true,"fork":false,"pushed_at":"2018-10-16T22:55:22.000Z","size":15508,"stargazers_count":719,"open_issues_count":13,"forks_count":103,"subscribers_count":53,"default_branch":"master","last_synced_at":"2025-05-01T12:04:54.249Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://oracle.github.io/graphpipe","language":"Makefile","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/oracle.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-06-27T18:31:23.000Z","updated_at":"2025-02-21T23:45:18.000Z","dependencies_parsed_at":"2022-09-19T08:01:52.532Z","dependency_job_id":null,"html_url":"https://github.com/oracle/graphpipe","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle%2Fgraphpipe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle%2Fgraphpipe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle%2Fgraphpipe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oracle%2Fgraphpipe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oracle","download_url":"https://codeload.github.com/oracle/graphpipe/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253580333,"owners_count":21930928,"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":"2024-08-03T18:01:23.347Z","updated_at":"2025-05-11T14:34:49.046Z","avatar_url":"https://github.com/oracle.png","language":"Makefile","funding_links":[],"categories":["Model Serving"],"sub_categories":[],"readme":"\u003cimg\n    src=\"./docs/assets/logo.png\"\n    width=\"500\"\n    style=\"display: block; width: 500px; margin: auto; margin-bottom: 3em\"\n/\u003e\n\n# GraphPipe\n\n\u003e Machine Learning Model Deployment Made Simple\n\n# What is it?\n\nGraphPipe is a protocol and collection of software designed to simplify machine\nlearning model deployment and decouple it from framework-specific model\nimplementations.\n\nThe existing solutions for model serving are inconsistent and/or inefficient.\nThere is no consistent protocol for communicating with these model servers so\nit is often necessary to build custom clients for each workload. GraphPipe\nsolves these problems by standardizing on an efficient communication protocol\nand providing simple model servers for the major ML frameworks.\n\nWe hope that open sourcing GraphPipe makes the model serving landscape a\nfriendlier place.  See more about why we built it\n[here](https://oracle.github.io/graphpipe/#/guide/user-guide/overview).\n\nOr browse the rest of the [documentation](https://oracle.github.io/graphpipe).\n\n# Features\n\n* A minimalist machine learning transport specification based on [flatbuffers]\n* Simple, efficient reference model servers for [Tensorflow], [Caffe2], and [ONNX].\n* Efficient client implementations in Go, Python, and Java.\n\n[flatbuffers]: https://google.github.io/flatbuffers/\n[Tensorflow]: https://www.tensorflow.org\n[Caffe2]: https://caffe2.ai\n[ONNX]: https://onnx.ai\n\n# What is in this repo?\nThis repo contains documentation as well as the flatubuffer definition files\nthat are used by other language specific repos.  If you are looking for\nGraphPipe clients, servers, and example code, check out our other GraphPipe\nrepos:\n\n  - https://github.com/oracle/graphpipe-go - the GraphPipe go client library\n  - https://github.com/oracle/graphpipe-go/tree/master/cmd/graphpipe-tf -\n    Go implementation of a GraphPipe TensorFlow model server\n  - https://github.com/oracle/graphpipe-go/tree/master/cmd/graphpipe-onnx -\n    a Go implementation a GraphPipe ONNX/Caffe2 model server\n  - https://github.com/oracle/graphpipe-py - the GraphPipe client library for\n    Python\n  - https://github.com/oracle/graphpipe-tf-py  - a Python implementation of\n    a remote operation client for TensorFlow, as well as some example server\n    implementations\n\n## Building flatbuffer definitions\n\nIf you've got flatc installed you can just `make all` but if you don't want\nto install it, you can `export USE_DOCKER=1` and then `make all`. (Remember,\nmake needs vars exported, not just on the command-line where you run make).\n\nThis will produce the go, c, and python libraries, which can then be copied\ninto their projects graphpipe-go, graphpipe-tf-py, and graphpipe-py,\nrespectively.\n\n## Contributing\n\nAll of the GraphPipe projects are open source. To find out how to contribute\nsee [CONTRIBUTING.md](CONTRIBUTING.md)\n\nYou can also chat us up on our [Slack Channel](https://join.slack.com/t/graphpipe/shared_invite/enQtNDE4MTUyODk2NzQzLTUwODlkZDRiYTI4NmE1OTA5NzRmNjk5MGZiY2M0ZDRiYzNiMTQ0ZmIxODYzZjY2NzRmNzM4NTI0OGVlZGYzZTA).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/oracle.github.io%2Fgraphpipe%2F","html_url":"https://awesome.ecosyste.ms/projects/oracle.github.io%2Fgraphpipe%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/oracle.github.io%2Fgraphpipe%2F/lists"}