# TPI-LLM
**Entity class:** Distributed inference research system
**As of:** November 17, 2026
## Definition
**TPI-LLM** is a research system for serving large language models with tensor parallelism across constrained edge devices. 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
- **comparator:** [[wiki/prima.cpp|prima.cpp]].
- **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
- [TPI-LLM — project record or attributed account](https://arxiv.org/abs/2410.00531).