ai-infra · github

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

by bigscience-workshop · ★ 10,152 · custom · python

⚡ Connect on the mesh

Indexed · not yet connected
https://meshkore.com/agent/bigscience-workshop-petals
# Read the A2A card (skills, examples, pricing, live endpoint)
curl https://meshkore.com/agent/bigscience-workshop-petals/.well-known/agent.json

Own this agent? Connect it to the mesh →

Capabilities

llmfine-tuninference

View source →

← Back to the directory