{"data":{"slug":"prunaai-pruna","name":"pruna","tagline":"Model optimization framework for developers","github_url":"https://github.com/PrunaAI/pruna","owner":"PrunaAI","repo":"pruna","owner_avatar_url":"https://avatars.githubusercontent.com/u/113530019?v=4","primary_language":"Python","stars":1263,"forks":102,"topics":["ai","computer-vision","deep-learning","diffusers","diffusion-models","hacktoberfest","llm","machine-learning","optimization","python","speech-recognition","transformers"],"archived":false,"github_pushed_at":"2026-07-29T09:01:13+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/prunaai-pruna","markdown_url":"https://www.graphcanon.com/tools/prunaai-pruna.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/prunaai-pruna","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=prunaai-pruna","description":"Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.","homepage_url":"https://docs.pruna.ai","license":"Apache-2.0","open_issues":15,"watchers":11,"ai_summary":"Pruna is designed to help developers deliver faster and more efficient AI models with ease.","readme_excerpt":"## <img src=\"./docs/assets/images/pruna_cool.png\" alt=\"Pruna Cool\" width=20></img> Installation\n\nPruna is currently available for installation on Linux, MacOS and Windows. However, some algorithms impose restrictions on the operating system and might not be available on all platforms.\n\nBefore installing, ensure you have:\n- Python 3.9 or higher\n- Optional: [CUDA toolkit](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/) for GPU support\n\n#### Option 1: Install Pruna using pip\n\nPruna is available on PyPI, so you can [install it using pip](https://docs.pruna.ai/en/stable/setup/install.html):\n\n```bash\npip install pruna\n```\n\n#### Option 2: Install Pruna from source\n\nYou can also install Pruna directly from source by cloning the repository and installing the package in editable mode:\n\n```bash\ngit clone https://github.com/PrunaAI/pruna.git\ncd pruna\npip install -e .\n```\n\n---\n\n## <img src=\"./docs/assets/images/pruna_cool.png\" alt=\"Pruna Cool\" width=20></img> Quick Start\n\n\nGetting started with Pruna is easy-peasy pruna-squeezy!\n\nFirst, load any pre-trained model. Here's an example using Stable Diffusion:\n\n```python\nfrom diffusers import StableDiffusionPipeline\nbase_model = StableDiffusionPipeline.from_pretrained(\"stable-diffusion-v1-5/stable-diffusion-v1-5\")\n```\n\nThen, use Pruna's `smash` function to optimize your model. Pruna provides a variety of different optimization algorithms, allowing you to combine different algorithms to get the best possible results. You can customize the optimization process using `SmashConfig`:\n\n```python\nfrom pruna import smash, SmashConfig","github_created_at":"2025-03-11T14:03:49+00:00","created_at":"2026-07-11T12:26:15.151805+00:00","updated_at":"2026-07-31T12:00:23.232096+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"computer-vision","name":"computer-vision"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"diffusers","name":"diffusers"},{"slug":"diffusion-models","name":"diffusion-models"},{"slug":"hacktoberfest","name":"hacktoberfest"},{"slug":"llm","name":"llm"},{"slug":"machine-learning","name":"machine-learning"}],"trust":{"provenance":{"is_fork":false,"github_id":946676136,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-31T12:00:22.236Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":2,"last_release_at":"2026-06-22T13:43:50Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:26:20.463Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-31T12:00:22.740Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-31T12:00:22.740Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-31T12:00:22.740Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- You need to optimize pre-trained models like those from Stable Diffusion for better performance.","- Your project requires customization of the optimization process through `SmashConfig`, offering flexibility with various algorithms.","- The development environment supports Python 3.9 or higher and is either Linux, MacOS, or Windows."],"when_not_to_use":["- When the specific model you wish to optimize does not benefit from Pruna's supported optimization algorithms.","- If your project's operating system requirements are outside of Linux, MacOS, or Windows platforms as Pruna might not support all required OS features.","- Your Python version is below 3.9, which is a requirement for using Pruna."],"source":"enrich:decision_facts","observed_at":"2026-07-16T23:16:38.511Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Pruna is a Python framework focused on delivering quicker and leaner AI models for developers across Linux, MacOS, and Windows platforms."}]}}