---
title: "TensorFold"
description: "The inference engine that serves the cluster's models today."
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.c4e.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# TensorFold

TensorFold is the engine serving the cluster's models right now. It runs as a Slurm job across both Sparks, splitting DeepSeek V4.1 Flash between them over the 200 Gb/s link, and serves every model variant from that one copy. The engine is swappable: any OpenAI-compatible engine, such as NVIDIA NIM, can replace it behind [LiteLLM](https://docs.c4e.ai/stack/litellm/) without changing model names.

## Official docs

- [TensorFold](https://github.com/ashhart/TensorFold)

Source: https://docs.c4e.ai/stack/tensorfold/index.mdx
