# Pipeline not using GPU

**URL:** <https://discuss.huggingface.co/t/pipeline-not-using-gpu/74776>\
**Category:** Beginners\
**Created:** [February 26, 2024, 6:13am UTC](https://discuss.huggingface.co/t/pipeline-not-using-gpu/74776 "2024-02-26T06:13:36Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![hannahmc](https://avatars.discourse-cdn.com/v4/letter/h/dbc845/32.png) [@hannahmc](https://discuss.huggingface.co/u/hannahmc)\
**Post date:** [February 26, 2024, 6:13am UTC](https://discuss.huggingface.co/t/pipeline-not-using-gpu/74776/1 "2024-02-26T06:13:36Z")

</div>

Hi,

I’m using a simple pipeline on Google Colab but GPU usage remains at 0 when performing inference on a large number of text inputs (according to Colab monitor).

Here’s what I’ve tried:

```auto
model = pipeline("feature-extraction", device=torch.device("cuda"))
model = pipeline("feature-extraction", device=0)

```

I can confirm that I’m using a T4-GPU runtime. Neither uses GPU.

Transformers version: 4.37.2  
CUDA version:  
nvcc: NVIDIA (R) Cuda compiler driver  
Copyright (c) 2005-2023 NVIDIA Corporation  
Built on Tue\_Aug\_15\_22:02:13\_PDT\_2023  
Cuda compilation tools, release 12.2, V12.2.140  
Build cuda\_12.2.r12.2/compiler.33191640\_0