# Pipeline inference with multi gpus

**URL:** <https://discuss.huggingface.co/t/pipeline-inference-with-multi-gpus/15660>\
**Category:** Beginners\
**Created:** [March 13, 2022, 7:11pm UTC](https://discuss.huggingface.co/t/pipeline-inference-with-multi-gpus/15660 "2022-03-13T19:11:18Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![crsegerie](https://avatars.discourse-cdn.com/v4/letter/c/41988e/32.png) [@crsegerie](https://discuss.huggingface.co/u/crsegerie)\
**Post date:** [March 13, 2022, 7:11pm UTC](https://discuss.huggingface.co/t/pipeline-inference-with-multi-gpus/15660/1 "2022-03-13T19:11:18Z")

</div>

Hello, with the pipeline object, is it possible to perform inferences with my 2 gpus at the same time ?

What I would like is something like:

```auto
    out = pipe(
        input,
        batch_size=batch_size,
        n_gpus=2 # <- Is there an equivalent to this argument ?

    )

```