{"id":18368701,"url":"https://github.com/radanalyticsio/tensorflow-serving-gpu-s2i","last_synced_at":"2025-06-14T20:33:56.456Z","repository":{"id":72027200,"uuid":"108865460","full_name":"radanalyticsio/tensorflow-serving-gpu-s2i","owner":"radanalyticsio","description":"S2I image for running tensorflow_model_server on Openshift with GPU","archived":false,"fork":false,"pushed_at":"2017-12-07T15:47:18.000Z","size":7,"stargazers_count":3,"open_issues_count":2,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-06T17:37:41.252Z","etag":null,"topics":["gpu","openshift","s2i","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Shell","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/radanalyticsio.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":"2017-10-30T14:52:13.000Z","updated_at":"2019-09-30T16:46:22.000Z","dependencies_parsed_at":null,"dependency_job_id":"fb7d4d4a-3460-4fa6-b3e8-f4d916a3f969","html_url":"https://github.com/radanalyticsio/tensorflow-serving-gpu-s2i","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/radanalyticsio/tensorflow-serving-gpu-s2i","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radanalyticsio%2Ftensorflow-serving-gpu-s2i","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radanalyticsio%2Ftensorflow-serving-gpu-s2i/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radanalyticsio%2Ftensorflow-serving-gpu-s2i/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radanalyticsio%2Ftensorflow-serving-gpu-s2i/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/radanalyticsio","download_url":"https://codeload.github.com/radanalyticsio/tensorflow-serving-gpu-s2i/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radanalyticsio%2Ftensorflow-serving-gpu-s2i/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259879932,"owners_count":22925854,"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":["gpu","openshift","s2i","tensorflow"],"created_at":"2024-11-05T23:27:06.641Z","updated_at":"2025-06-14T20:33:56.437Z","avatar_url":"https://github.com/radanalyticsio.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Radanalytics Tensorflow Serving  GPU#\n\nThis S2I image is for running on Openshift with GPU.With CUDA-9 and CuDNN-7.\nThis is a builder image for a tensorflow serving applications. It is\nmeant to be used in an openshift project with tensorflow models.\n\nThe final image will have tensorflow model installed along with `tensorflow_model_server` binary from submod/tf-server:cuda9-cudnn7-centos7, a startup script and associated\nutilities to start tensorflow prediction endpoint at port `6006`.\n\n## Integration With OpenShift\n\nTo make it easier to deploy a tensorflow serving endpoint a template for OpenShift is also included. This can be loaded into your project using:\n\n```\noc create -f https://raw.githubusercontent.com/sub-mod/tensorflow-serving-gpu-s2i/master/template.json\n```\n\nOnce loaded, select the ``tensorflow-server-gpu`` template from the web console.\nThe ``APPLICATION_NAME`` , ``SOURCE_REPOSITORY``  and ``SOURCE_DIRECTORY``must be specified.\n\nOR\n\nYou can create from commandline.Just create a new application within OpenShift, pointing the S2I builder at the Git repository containing your tensorflow model files.\n\n```\noc new-app --template=tensorflow-server-gpu \\\n\t--param=APPLICATION_NAME=tf-cnn-gpu \\\n\t--param=SOURCE_REPOSITORY=https://github.com/sub-mod/mnist-models \\\n\t--param=SOURCE_DIRECTORY=gpu/cnn\n\n```\nTo have any changes to your model automatically redeployed when changes are pushed back up to your Git repository, you can use the [web hooks integration](https://docs.openshift.com/container-platform/latest/dev_guide/builds.html#webhook-triggers) of OpenShift to create a link from your Git repository hosting service back to OpenShift.\n\n## Producing a build image ##\n\nTo produce a builder image:\n\n    $ make build\n\nTo print usage information for the builder image:\n\n    $ sudo docker run -t \u003cid from the make\u003e\n\nTo poke around inside the builder image:\n\n    $ sudo docker run -i -t \u003cid from the make\u003e\n    bash-4.2$ cd /opt/app-root # take a look around\n\nTo tag and push a builder image:\n\n    $ sudo make push\n\nBy default this will tag the image as `submod/tensorflow-serving-s2i-gpu`,\nedit the Makefile and change `PUSH_IMAGE` to control this.\n\n## s2i bin files ##\n\nS2i scripts are located at `./s2i/bin`.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fradanalyticsio%2Ftensorflow-serving-gpu-s2i","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fradanalyticsio%2Ftensorflow-serving-gpu-s2i","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fradanalyticsio%2Ftensorflow-serving-gpu-s2i/lists"}