# Get started

Set up vLLM Neuron and run your first inference — from install through your first API request.

::::{grid} 1 1 2 2
:gutter: 3

:::{grid-item-card} Setup guide
:link: setup-guide
:link-type: doc

Install and configure vLLM Neuron on Trainium or Inferentia.
:::

:::{grid-item-card} Online serving quickstart
:link: quickstart-online-serving
:link-type: doc

Launch an OpenAI-compatible API server and send your first chat request.
:::

:::{grid-item-card} Offline serving quickstart
:link: quickstart-offline-serving
:link-type: doc

Run batch inference with the `vllm.LLM` Python API.
:::

:::{grid-item-card} Migration from NxD Inference
:link: migration-nxdi-to-vllm-neuron
:link-type: doc

Migrate existing NxDI deployments to vLLM Neuron.
:::

::::

:::{toctree}
:maxdepth: 1
:hidden:

Setting up <setup-guide>
Online serving quickstart <quickstart-online-serving>
Offline serving quickstart <quickstart-offline-serving>
Migrating from NxDI <migration-nxdi-to-vllm-neuron>
:::