lancedb/docs/web/indexing/gpu-indexing.mdx

---
title: "GPU Indexing"
sidebarTitle: "GPU Indexing"
description: "Build a vector index faster with GPU acceleration, manually in LanceDB Embedded or automatically in LanceDB Enterprise."
icon: "microchip"
keywords: ["gpu", "gpu indexing", "cuda", "mps", "ivf_pq", "index build"]
availability:
  embedded: available
  enterprise: available
---

import {
    PyGpuIndexCuda as GpuIndexCuda,
    PyGpuIndexMps as GpuIndexMps,
} from '/snippets/indexing.mdx';

GPU acceleration can reduce the time needed to build vector indexes on large
datasets. Actual build time depends on the index configuration, vector
dimensions, storage throughput and available GPU resources.

<Info>
**Automatic GPU indexing**

Automatic GPU Indexing is currently only available in [LanceDB Enterprise](/index#architecture).
Please [contact us](https://www.lancedb.com/contact) to enable this feature for your deployment.

The vector index is created when you call `create_index`. The backend uses GPU resources
to build `IVF_PQ` indexes, with the number of GPUs set by the deployment's configuration.

This process is also asynchronous by default, but you can use `wait_for_index` to convert it
into a synchronous process by waiting until the index is built.

</Info>

`wait_for_index(...)` waits for the index to exist and for `index_stats(...)` to report `num_unindexed_rows == 0`. It can time out if the table is receiving continuous writes while the build is trying to catch up.

GPU acceleration changes how the vector index is built, not the lifecycle after the build. In the
embedded library, rows appended later still need `optimize()` before they are part of the index; a
deployment adds them in the background -- see [Incremental Indexing](/indexing/incremental-indexing).
`fast_search()` only searches indexed rows.

## Manual GPU indexing in LanceDB Embedded {#gpu-manual-gpu-indexing-in-lancedb-oss}

You can use the Python SDK to manually create the `IVF_PQ` index on a GPU. You'll need
[PyTorch>2.0](https://pytorch.org/). Note that GPU-based indexing is currently only
supported by the synchronous SDK in LanceDB Embedded.

Specify the values `cuda` or `mps` (on Apple Silicon) for the `accelerator` parameter
to enable GPU training on your device.

### GPU indexing on Linux {#gpu-gpu-indexing-on-linux}

<CodeGroup>
    <CodeBlock filename="Python" language="Python" icon="python">
    {GpuIndexCuda}
    </CodeBlock>
</CodeGroup>

### GPU indexing on macOS (Apple Silicon) {#gpu-gpu-indexing-on-macos-apple-silicon}

<CodeGroup>
    <CodeBlock filename="Python" language="Python" icon="python">
    {GpuIndexMps}
    </CodeBlock>
</CodeGroup>

## Performance considerations {#gpu-performance-considerations}

- GPU memory usage scales with `num_partitions` and vector dimensions
- Size GPU memory for the training batches and index configuration
- Monitor memory use while choosing training batch sizes
- Measure build time and recall before changing training settings

## Troubleshooting {#gpu-troubleshooting}

If you encounter the error `AssertionError: Torch not compiled with CUDA enabled`,
you need to [install PyTorch with CUDA support](https://pytorch.org/get-started/locally/).

## What to read next {#next}

<CardGroup cols={2}>
  <Card title="Incremental Indexing" icon="refresh" href="/indexing/incremental-indexing">
    Keeping an index up-to-date as new data arrives.
  </Card>
  <Card title="GPU Function Execution" icon="microchip" href="/curation/gpu-function-execution">
    How a GPU-bound Function's worker gets scheduled -- the same GPU-placement story for Functions instead of index builds.
  </Card>
</CardGroup>