{"id":26076744,"url":"https://github.com/coela-oss/devino","last_synced_at":"2026-05-16T11:32:41.704Z","repository":{"id":281305016,"uuid":"943933684","full_name":"coela-oss/devino","owner":"coela-oss","description":"Practical guide for performing local inference on LLM on a laptop equipped with an Intel Iris GPU, even if you do not have an Nvidia GPU.","archived":false,"fork":false,"pushed_at":"2025-03-19T14:30:21.000Z","size":439,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-04T04:24:20.318Z","etag":null,"topics":["dockerdesktop","huggingface","intel","openvino","windows","wsl"],"latest_commit_sha":null,"homepage":"","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/coela-oss.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-03-06T14:05:48.000Z","updated_at":"2025-03-19T14:30:26.000Z","dependencies_parsed_at":"2025-09-05T20:57:34.556Z","dependency_job_id":null,"html_url":"https://github.com/coela-oss/devino","commit_stats":null,"previous_names":["coela-oss/devino"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/coela-oss/devino","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coela-oss%2Fdevino","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coela-oss%2Fdevino/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coela-oss%2Fdevino/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coela-oss%2Fdevino/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/coela-oss","download_url":"https://codeload.github.com/coela-oss/devino/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coela-oss%2Fdevino/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33100841,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-16T04:41:52.686Z","status":"ssl_error","status_checked_at":"2026-05-16T04:41:52.009Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["dockerdesktop","huggingface","intel","openvino","windows","wsl"],"created_at":"2025-03-09T02:13:02.121Z","updated_at":"2026-05-16T11:32:41.685Z","avatar_url":"https://github.com/coela-oss.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Project Overview\n\nThis repository provides an environment for leveraging OpenVINO and OneAPI to enable LLM inference on Intel devices. It includes scripts for setting up an Ubuntu-based environment, converting models to OpenVINO IR format, and deploying an OpenVINO model server.\n\n## Repository Structure\n\n- [setup](./setup): Provides scripts for setting up a Pytorch-XPU environment using Ubuntu 22 and Poetry.\ninstallation.\n- Model Directories: Named according to Hugging Face model IDs, each containing conversion and inference scripts based on the setup environment.\n- [playground](./playground/): Contains sample scripts tested in an OpenVINO 2025 and Ubuntu 24 environment.\n\n## Key Features\n\n- **OpenVINO IR Conversion**: Converts Hugging Face models to OpenVINO IR format for optimized inference.\n- **OpenVINO Model Server (OVMC)**: Implements an OpenVINO model server for running converted models.\n- **GPU Acceleration**: Provides performance improvements for inference using Intel GPUs.\n\n## Getting Started\n\n1. **Verify Ubuntu Compatibility**: Check the appropriate WSL Ubuntu version using [intel-gpu-wsl-advisor](https://github.com/coela-oss/intel-gpu-wsl-advisor).\n  -  intel-gpu-wsl-advisor repo is a prerequisite repository to determine the appropriate Ubuntu version for WSL \n2. **Setup Environment**: Use the scripts in `setup/` to install dependencies and configure Pytorch-XPU.\n3. **Convert Models**: Run the provided conversion scripts to transform models into OpenVINO IR format.\n4. **Deploy Model Server**: Install OpenVINO GenAI's OVMC server and execute converted models. by [Makefile](./Makefile)\n\n## References\n\n- [OpenVINO Documentation (2025)](https://docs.openvino.ai/2025/index.html)\n- [Hugging Face Optimum-Intel](https://huggingface.co/blog/deploy-with-openvino)\n\nThis repository is under active development, integrating new features for optimized inference and deployment on Intel hardware.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoela-oss%2Fdevino","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcoela-oss%2Fdevino","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoela-oss%2Fdevino/lists"}