{"name":"github_","repo":"byted-technologies/github_","url":"https://midorreal.com/project/fractal-compute-orchestrations-github","repository":"https://github.com/byted-technologies/github_","description":"Official Fractal Compute Orchestrations ecosystem hub (v3.1 non-commercial source-available): FractalWorkspace, FractalCore (v1.0.0), and FractalAndroid.","facts":{"homepage":{"value":"https://github.com/Fractal-Compute-Orchestrations/FractalWorkspace","source":"https://github.com/Fractal-Compute-Orchestrations/FractalWorkspace","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/byted-technologies/github_/releases","checked":"20 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/byted-technologies/github_/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/byted-technologies/github_","checked":"22 Nov 2026"}},"stars":773.0,"writeup":{"what_it_is":"Fractal Compute Orchestrations is a set of three repositories for distributed edge AI: FractalWorkspace (umbrella and benchmarks), FractalCore (a Python SDK, CLI and federated coordinator, v1.0.0), and FractalAndroid (an Android edge client). The project covers INT4 quantized transport, federated learning, thermal-gated on-device training, and split LLM inference.","audience":"Researchers and developers working on federated learning and on-device AI on mobile hardware","claims":[{"kind":"specific","claim":"Reduces TinyLlama-1.1B wire payloads by 7.1x","excerpt":"cutting TinyLlama-1.1B wire payloads by **7.1x** (`4,196 MB -> 590 MB`)","status":"not_checked"},{"kind":"specific","claim":"Preserves 0.9878 mean layer cosine similarity","excerpt":"while preserving **0.9878** mean layer cosine similarity","status":"not_checked"},{"kind":"specific","claim":"Gates Android training on SoC temperature of 40.0 C or below","excerpt":"strictly when SoC thermals (`<= 40.0 C` and non-severe thermal status)","status":"not_checked"},{"kind":"specific","claim":"Limits edge partitions to 150 MB","excerpt":"Isolates decoder partitions under a `150 MB` edge RAM envelope","status":"not_checked"},{"kind":"specific","claim":"Provides a Colab quickstart demo","excerpt":"[![Open In Colab](https://img.shields.io/badge/Colab-Quickstart_Demo-black","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":17,"reality":25,"gap":-8,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-26T06:04:48+00:00","text":"Repository created","source":"https://github.com/byted-technologies/github_"}],"cite":"github_ is a GitHub project at https://github.com/byted-technologies/github_, described there as \"Official Fractal Compute Orchestrations ecosystem hub (v3.1 non-commercial source-available): FractalWorkspace, FractalCore (v1.0.0), and FractalAndroid\".","attribution":"Data from Mid or Real, https://midorreal.com/project/fractal-compute-orchestrations-github, checked 22 November 2026. Attribution with a link is required.","still_real":null}