# Petals **Entity class:** Distributed inference project **As of:** November 17, 2026 ## Definition **Petals** is a system for serving large language models across internet-connected machines by allocating transformer layer blocks to different hosts. This node belongs to the **distributed inference** route of [[wiki/Distributed Compute Ecosystem|Distributed Compute Ecosystem]], which records the specific kind of work or network capacity involved. ## Relationships - **model demonstration:** [[wiki/BLOOM-176B|BLOOM-176B]]. - **mechanism route:** [[wiki/Distributed Compute Ecosystem|Distributed Compute Ecosystem]]. - **source article:** [[articles/Embedded Super-Spreader Events and Muse|Embedded Super-Spreader Events and Muse]]. ## Sources - [Petals — project record or attributed account](https://arxiv.org/abs/2209.01188).