{"id":19228113,"url":"https://github.com/unit-mesh/edge-infer","last_synced_at":"2025-04-21T01:32:00.043Z","repository":{"id":206378775,"uuid":"715927875","full_name":"unit-mesh/edge-infer","owner":"unit-mesh","description":"EdgeInfer enables efficient edge intelligence by running small AI models, including embeddings and OnnxModels, on resource-constrained devices like Android, iOS, or MCUs for real-time decision-making. EdgeInfer 旨在资源受限的设备上运行小型 AI 模型（包括向量化和 Onnx 模型），如 Android、iOS 或 MCUs，实现高效的边缘智能，用于实时决策。","archived":false,"fork":false,"pushed_at":"2024-04-17T09:23:00.000Z","size":280,"stargazers_count":43,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-01T07:54:14.530Z","etag":null,"topics":["inference","llm"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/unit-mesh.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":"2023-11-08T05:40:33.000Z","updated_at":"2025-04-01T06:33:08.000Z","dependencies_parsed_at":"2024-11-09T15:38:27.617Z","dependency_job_id":null,"html_url":"https://github.com/unit-mesh/edge-infer","commit_stats":null,"previous_names":["unit-mesh/native-embedding","unit-mesh/inference","unit-mesh/edge-inference","unit-mesh/edge-embedding","unit-mesh/edge-infer"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unit-mesh%2Fedge-infer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unit-mesh%2Fedge-infer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unit-mesh%2Fedge-infer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unit-mesh%2Fedge-infer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/unit-mesh","download_url":"https://codeload.github.com/unit-mesh/edge-infer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249982561,"owners_count":21355719,"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":["inference","llm"],"created_at":"2024-11-09T15:26:46.575Z","updated_at":"2025-04-21T01:31:59.414Z","avatar_url":"https://github.com/unit-mesh.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/logo.svg\" width=\"160px\" height=\"160px\"  alt=\"logo\" /\u003e\n\u003c/p\u003e\n\u003ch1 align=\"center\"\u003eEdge Infer\u003c/h1\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"(https://github.com/unit-mesh/edge-infer/actions/workflows/rust.yml\"\u003e\n    \u003cimg src=\"https://github.com/unit-mesh/edge-infer/actions/workflows/ci.yml/badge.svg\" alt=\"Build\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://crates.io/crates/enfer_core\"\u003e\n    \u003cimg src=\"https://img.shields.io/crates/v/enfer_core\" alt=\"Crates.io\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003e EdgeInfer enables efficient edge intelligence by running small AI models, including embeddings and OnnxModels, on\n\u003e resource-constrained devices like Android, iOS, or MCUs for real-time decision-making.\n\nArchitecture:\n\n\u003cimg src=\"./docs/edge-mind.svg\" width=\"320px\" alt=\"EdgeMind Architecture\" /\u003e\n\nPlatform support (by Design):\n\n- Android, iOS\n- Linux, Windows, Mac,\n- Raspberry Pi, MCU\n\n## Todos\n\n- [x] Inference wrapper\n    - [x] Onnx Runtime\n    - [x] Tokenizer\n- [x] [UniFFI](https://github.com/mozilla/uniffi-rs), is a toolkit for building cross-platform software components in\n  Rust.\n- [ ] GRPC server with [tonic](https://github.com/hyperium/tonic)\n- [ ] Multiple OS support:\n    - Desktop: Windows, Mac, Linux (x86, x64)\n    - Mobile: Android, iOS, Linux (ARM)\n    - Embedded Linux (ARM).\n- [ ] Flexible Configuration: Easily configurable via command-line parameters, including listening port, batch size,\n  thread count, and others.\n\n## Usecases\n\n- [ ] SearchEverywhere: Search for anything, anywhere, anytime.\n    - Model: Embedding,\n      like [Sentence-Transformers MiniLM](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)\n    - Extra: Local Indexing\n- [ ] Visualization\n    - Model: [Ultralytics YOLOv9](https://github.com/ultralytics/ultralytics)\n- [ ] AutoComplete\n    - Model: Embedding with ??\n- [ ] Summarization\n\n## Resources\n\nExamples:\n\n- Modern cross-platform telemetry: [Glean](https://github.com/mozilla/glean)\n\n### MCU\n\nToSpike\n\n- ESP32: [esp-rs](https://github.com/esp-rs)\n- Raspberry Pi Classic\n    - [built-onnxruntime-for-raspberrypi-linux](https://github.com/nknytk/built-onnxruntime-for-raspberrypi-linux)\n    - [ONNX Runtime IoT Deployment on Raspberry Pi](https://onnxruntime.ai/docs/tutorials/iot-edge/rasp-pi-cv.html)\n\nNot working:\n\n- Arduino M0 Pro, Flash: 256 KB, SRAM: 32Kb\n    - Official: [Arduino M0 Pro](https://docs.arduino.cc/retired/boards/arduino-m0-pro)\n    - Rust's [cortex-m-quickstart](https://github.com/rust-embedded/cortex-m-quickstart)\n- Raspberry Pi Zero W, Flash: 512 MB, SRAM: 512 MB\n    - Official: [Raspberry Pi Zero W](https://www.raspberrypi.com/products/raspberry-pi-zero/)\n    - [Using Rust to Control a Raspberry Pi Zero W Rover](https://disconnected.systems/blog/rust-powered-rover/)\n    - Not working reason: See in [inference_rpi](inference_rpi/README.md)\n\n## License\n\nThis project is licensed under the MIT License, See [LICENSE](LICENSE) for the full license text.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funit-mesh%2Fedge-infer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funit-mesh%2Fedge-infer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funit-mesh%2Fedge-infer/lists"}