{"id":18264569,"url":"https://github.com/modeltc/nart","last_synced_at":"2025-04-04T21:30:42.799Z","repository":{"id":41387309,"uuid":"509384008","full_name":"ModelTC/NART","owner":"ModelTC","description":"NART = NART is not A RunTime, a deep learning inference framework.","archived":false,"fork":false,"pushed_at":"2023-03-02T14:50:37.000Z","size":5854,"stargazers_count":38,"open_issues_count":1,"forks_count":13,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-03-20T19:15:31.869Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","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/ModelTC.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2022-07-01T08:48:27.000Z","updated_at":"2024-09-06T03:42:10.000Z","dependencies_parsed_at":"2024-11-05T11:16:28.382Z","dependency_job_id":null,"html_url":"https://github.com/ModelTC/NART","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FNART","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FNART/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FNART/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FNART/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ModelTC","download_url":"https://codeload.github.com/ModelTC/NART/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247251976,"owners_count":20908603,"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":"2024-11-05T11:15:11.939Z","updated_at":"2025-04-04T21:30:38.273Z","avatar_url":"https://github.com/ModelTC.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NART\n\n## Introduction\n\n\u003e What is NART?\n\n**NART** = **N**ART is not **A** **R**un**T**ime\n\nNART is a deep learning inference framework.\n\nNART supports multiple types of deep learning models and multiple back-ends.\n\n## License\n\nNART is licensed under the [Apache-2.0](LICENSE) license.\n\n## Requirements\n\n- pybind11\n- numpy\n- onnx\u003e=1.4.0\n- sphinx (for doc)\n- sphinxcontrib-contentui (for doc)\n- protobuf\u003e=3.5.1 (python package and compiler)\n\n### Model conversion\n\nThe below are versions supported by the model conversion module:\n\n- PyTorch: 0.3, 0.4, 1.0, 1.1, 1.2, 1.3, 1.5, 1.8\n\nNote: for Caffe target, some layers may be invalid for official Caffe,\nwhich will be fixed in later releases.\n\n## Build\n\n```sh\n# update git submodules\ngit submodule update --init --recursive\n\n# install python requirements\npip install -r python/requirements.txt\n\ncmake -B build \\\n    -DNART_CASE_MODULES='quant;cuda;tensorrt' \\ # enable nart case modules in art/modules\n    -DENABLE_NART_TOOLS=ON                      # enable nart tools (e.g. promark)\n\ncmake --build build -j16\n```\n\n## Install\n\n```sh\n# set install prefix, change it to virtual env or some other desired path\nexport _NART_INSTALL_PREFIX=`pwd`/install\n\n# ensure libart.so can be found by nart tools\nexport LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$_NART_INSTALL_PREFIX/lib\n\n# install built modules\ncmake --install build --prefix $_NART_INSTALL_PREFIX\n\n# install python modules\ncd python\npython setup.py install --prefix $_NART_INSTALL_PREFIX\n```\n\n## Usage\n\n### Model inference deployment\n\nPlease refer to [this example](./examples/00-model-conversion-and-inference).\n\n### NART case runtime\n\nPlease refer to [this example](./examples/01-nart-case-cpu-example) and [`nart_promark`](./tools/promark.cpp).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmodeltc%2Fnart","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmodeltc%2Fnart","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmodeltc%2Fnart/lists"}