# Running ASR inference pipeline on multiple GPU's

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-asr-inference-pipeline-on-multiple-gpus%2F73818%3E%5C
**Category:** 🤗Transformers\
**Created:** [February 19, 2024, 1:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-asr-inference-pipeline-on-multiple-gpus%2F73818 "2024-02-19T13:07:16Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jssaluja](https://avatars.discourse-cdn.com/v4/letter/j/b4bc9f/32.png) [@jssaluja](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fjssaluja)%5C
**Post date:** [February 19, 2024, 1:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-asr-inference-pipeline-on-multiple-gpus%2F73818%2F1 "2024-02-19T13:07:16Z")

</div>

Kaggle notebook have access to 2 GPU’s.

I created two pipelines, set device = 0, device =1. This loaded the inference model in 2 GPU’s.

However, the inference pipeline ran on 1 GPU, while other GPU is idle.

Looking for pointers to run inference on 2 GPU’s in parallel