# benchmark

Python API: `modelconverter.platforms.rvc3.benchmark`

Benchmarking of converted models on RVC3 devices.

Loads the model through the OpenVINO inference engine onto the `VPUX` plugin of a connected RVC3 device and measures its
throughput and latency under a varying number of concurrent inference requests.

## Classes

### RVC3Benchmark

Benchmark of a converted model running on an RVC3 device.

#### Methods

##### benchmark

```python
def benchmark(configuration: Configuration) -> Result:
```

Run a single benchmark of the model on the device.

Parameters

 * `configuration` (`Configuration`): Configuration to benchmark with. The only supported option is `requests`, the number of
   concurrent inference requests.

Returns

 * `Result`: The measured throughput under `fps` and the median request latency under `latency`.

#### Attributes

##### all_configurations

Return the configurations used by the full benchmark.

Covers one to five concurrent inference requests.

##### default_configuration

Default configuration for RVC3 benchmarking.

 * `Options:`: requests: The number of requests to perform.