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

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# Diagnostics and errors

> Error raised when CUDA GPU runs out of memory during prediction.

<div className="python-reference-heading">
  <h2 id="tabpfncudaoutofmemoryerror">
    `TabPFNCUDAOutOfMemoryError`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/TabPFN/blob/c70b6ef0488858d32244c52222abfc0c5be207d6/src/tabpfn/errors.py#L137" aria-label="View source for TabPFNCUDAOutOfMemoryError"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Error raised when CUDA GPU runs out of memory during prediction.

```python theme={null}
TabPFNCUDAOutOfMemoryError(
    original_error: Exception | None = None,
    *,
    n_train_samples: int | None = None,
    n_test_samples: int | None = None,
    n_features: int | None = None,
    model_type: str = "classifier",
)
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="tabpfncudaoutofmemoryerror--original-error" /><code className="python-reference-parameter">original\_<wbr />error</code> | <code className="python-reference-type">Exception \| None</code> | `None` | — |
  | <span id="tabpfncudaoutofmemoryerror--n-train-samples" /><code className="python-reference-parameter">n\_<wbr />train\_<wbr />samples</code> | <code className="python-reference-type">int \| None</code> | `None` | — |
  | <span id="tabpfncudaoutofmemoryerror--n-test-samples" /><code className="python-reference-parameter">n\_<wbr />test\_<wbr />samples</code> | <code className="python-reference-type">int \| None</code> | `None` | — |
  | <span id="tabpfncudaoutofmemoryerror--n-features" /><code className="python-reference-parameter">n\_<wbr />features</code> | <code className="python-reference-type">int \| None</code> | `None` | — |
  | <span id="tabpfncudaoutofmemoryerror--model-type" /><code className="python-reference-parameter">model\_<wbr />type</code> | <code className="python-reference-type">str</code> | `"classifier"` | — |
</div>

***

<div className="python-reference-heading">
  <h2 id="tabpfnmpsoutofmemoryerror">
    `TabPFNMPSOutOfMemoryError`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/TabPFN/blob/c70b6ef0488858d32244c52222abfc0c5be207d6/src/tabpfn/errors.py#L143" aria-label="View source for TabPFNMPSOutOfMemoryError"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Error raised when MPS (Apple Silicon) runs out of memory during prediction.

```python theme={null}
TabPFNMPSOutOfMemoryError(
    original_error: Exception | None = None,
    *,
    n_train_samples: int | None = None,
    n_test_samples: int | None = None,
    n_features: int | None = None,
    model_type: str = "classifier",
)
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="tabpfnmpsoutofmemoryerror--original-error" /><code className="python-reference-parameter">original\_<wbr />error</code> | <code className="python-reference-type">Exception \| None</code> | `None` | — |
  | <span id="tabpfnmpsoutofmemoryerror--n-train-samples" /><code className="python-reference-parameter">n\_<wbr />train\_<wbr />samples</code> | <code className="python-reference-type">int \| None</code> | `None` | — |
  | <span id="tabpfnmpsoutofmemoryerror--n-test-samples" /><code className="python-reference-parameter">n\_<wbr />test\_<wbr />samples</code> | <code className="python-reference-type">int \| None</code> | `None` | — |
  | <span id="tabpfnmpsoutofmemoryerror--n-features" /><code className="python-reference-parameter">n\_<wbr />features</code> | <code className="python-reference-type">int \| None</code> | `None` | — |
  | <span id="tabpfnmpsoutofmemoryerror--model-type" /><code className="python-reference-parameter">model\_<wbr />type</code> | <code className="python-reference-type">str</code> | `"classifier"` | — |
</div>

***

<div className="python-reference-heading">
  <h2 id="display-debug-info">
    `display_debug_info`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/TabPFN/blob/c70b6ef0488858d32244c52222abfc0c5be207d6/src/tabpfn/misc/debug_versions.py#L652" aria-label="View source for display_debug_info"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Print useful debugging information.

```python theme={null}
display_debug_info()
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.