Self-host Text Generation Inference with Docker

Hugging Face's production inference server for transformer language models, with continuous batching and streaming.

This page describes the Levelrail template for Text Generation Inference (AI). It deploys the services below as one Docker Compose app on your own server.

Project site: https://huggingface.co/docs/text-generation-inference.

Recommended memory: about 8192 MiB.

This template reserves an NVIDIA GPU, so it needs a node with a GPU and the NVIDIA container runtime.

Services, ports and volumes

Service	Image	Container ports	Volumes
tgi	ghcr.io/huggingface/text-generation-inference:3.3.6	80	tgi_data -> /data

Environment variables

This template sets no environment variables.

Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.

Deploy Text Generation Inference with Levelrail

In the dashboard, open Apps, choose New app, then Browse templates, and select Text Generation Inference. Review the Compose body and deploy.

With the CLI:

levelrail-cli templates deploy text-generation-inference --name my-text-generation-inference

See Service template catalog for how templates work, and Getting started if you have not installed Levelrail yet.

More AI templates

• AnythingLLM
• ComfyUI
• Flowise
• Flowise (Postgres + Qdrant)
• Jupyter GPU Notebook
• Label Studio

All templates are listed in the self-host gallery.