{"id":19888269,"url":"https://github.com/project-codeflare/zero-copy-model-loading","last_synced_at":"2025-05-02T17:31:58.167Z","repository":{"id":40557360,"uuid":"408533304","full_name":"project-codeflare/zero-copy-model-loading","owner":"project-codeflare","description":"In-depth code associated with my Medium blog post, \"How to Load PyTorch Models 340 Times Faster with Ray\"","archived":false,"fork":false,"pushed_at":"2022-09-02T22:22:12.000Z","size":3724,"stargazers_count":17,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2023-08-29T03:45:00.383Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://medium.com/ibm-data-ai/how-to-load-pytorch-models-340-times-faster-with-ray-8be751a6944c","language":"Jupyter Notebook","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/project-codeflare.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}},"created_at":"2021-09-20T17:14:12.000Z","updated_at":"2023-07-19T16:22:40.000Z","dependencies_parsed_at":"2022-07-13T15:59:22.572Z","dependency_job_id":null,"html_url":"https://github.com/project-codeflare/zero-copy-model-loading","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/project-codeflare%2Fzero-copy-model-loading","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/project-codeflare%2Fzero-copy-model-loading/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/project-codeflare%2Fzero-copy-model-loading/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/project-codeflare%2Fzero-copy-model-loading/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/project-codeflare","download_url":"https://codeload.github.com/project-codeflare/zero-copy-model-loading/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224324498,"owners_count":17292521,"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":"2024-11-12T18:06:47.271Z","updated_at":"2024-11-12T18:06:47.347Z","avatar_url":"https://github.com/project-codeflare.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# zero-copy-model-loading\n\nCode to accompany the Medium post, [\"How to Load PyTorch Models 340 Times Faster\nwith\nRay\"](https://medium.com/ibm-data-ai/how-to-load-pytorch-models-340-times-faster-with-ray-8be751a6944c).\n\n## Notebooks\n\nNotebooks can be found in the `notebooks` directory:\n* `zero_copy_loading.ipynb`: The notebook that was used when authoring the \n  original blog post.\n* `benchmark/benchmark.ipynb`: The notebook that was used when authoring the\n  second post in the series.\n\nInstructions to run notebooks:\n1. Install `bash` and either `anaconda` or `miniconda`.\n1. Check out a copy of this repository and navigate to the root directory of\n   your local copy.\n1. Run the script `./env.sh`, which creates an Anaconda environment under \n   `\u003croot of your local copy\u003e/env`.\n   ```\n   ./env.sh\n   ```\n1. Activate the Anaconda environment:\n   ```\n   conda activate ./env\n   ```\n1. Run JupyterLab:\n   ```\n   jupyter lab\n   ```\n1. Navigate to the `notebooks` directory and open up the Jupyter notebook of your choice.\n\n\n## Python Package\n\nThis repository also contains the source code for the `zerocopy` library.\n`zerocopy` is a Python package that provides functions for implementing\nzero-copy model loading of PyTorch models on Ray.\n\nYou can find the source code for the package inside the `package` directory.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproject-codeflare%2Fzero-copy-model-loading","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fproject-codeflare%2Fzero-copy-model-loading","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproject-codeflare%2Fzero-copy-model-loading/lists"}