P
petals
bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
★10.5kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A open-source Data & Infrastructure project, built with Python, focusing on bloom and chatbot
Who made it?Maintained by bigscience-workshop team, 10.5K⭐ on GitHub, #184 out of 3133 in Data & Infrastructure
Why does it exist?With the growing demand for bloom and chatbot in Data & Infrastructure, bigscience-workshop created petals as a streamlined solution.
What can it do?Key use cases: deep-learning, distributed-systems, falcon
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/bigscience-workshop/petals | 官网 https://petals.dev
🔗 github.com/bigscience-workshop/petals | 官网 https://petals.dev
Topics
bloomchatbotdeep-learningdistributed-systemsfalcongptguanacolanguage-modelslarge-language-modelsllamamachine-learningmixtralneural-networksnlppipeline-parallelismpretrained-modelspytorchtensor-parallelismtransformervolunteer-computing