# Loading a converted model fails to recognize GPU

**URL:** <https://discourse.scverse.org/t/loading-a-converted-model-fails-to-recognize-gpu/944>\
**Category:** scvi-tools\
**Tags:** scvi\
**Created:** [November 21, 2022, 4:32pm UTC](https://discourse.scverse.org/t/loading-a-converted-model-fails-to-recognize-gpu/944 "2022-11-21T16:32:07Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![kateaugustyn](https://avatars.discourse-cdn.com/v4/letter/k/e19adc/32.png) [@kateaugustyn](https://discourse.scverse.org/u/kateaugustyn)\
**Post date:** [November 21, 2022, 4:32pm UTC](https://discourse.scverse.org/t/loading-a-converted-model-fails-to-recognize-gpu/944/1 "2022-11-21T16:32:07Z")

</div>

I have an scvi model created with scvi version ‘0.14.6’ using GPUs. I am now working in an updated environment (also using GPUs) with scvi version ‘0.19.0’. I did the following to convert the old model into the new format and to try and load the model but got the following error.

```auto
scvi.model.SCVI.convert_legacy_save(working_path + 
                                    "/scvi_model_Immune_batch10x/scvi_model_Immune_batch10x/",
                                    working_path + 
                                    "/new_scvi_model_Immune_batch10x/")

```

```auto
model = scvi.model.SCVI.load(working_path + 
                             "/new_scvi_model_Immune_batch10x/", 
                             adata, 
                             use_gpu=True)

```

```auto
INFO File /home/jupyter/new_scvi_model_Immune_batch10x/model.pt already downloaded                             
WARNING:jax._src.lib.xla_bridge:No GPU/TPU found, falling back to CPU. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)`

```

I already confirmed that scvi, pytorch, etc. were properly installed, that I have the expected CUDA version, and I confirmed that the converted model has the expected format. Is there any way I can make sure that loading the converted model will recognize the GPU?

---

<div class="post-metadata">

**Author:** ![adamgayoso](https://yyz1.discourse-cdn.com/flex035/user_avatar/discourse.scverse.org/adamgayoso/32/100_2.png) [@adamgayoso](https://discourse.scverse.org/u/adamgayoso)\
**Post date:** [November 21, 2022, 4:46pm UTC](https://discourse.scverse.org/t/loading-a-converted-model-fails-to-recognize-gpu/944/2 "2022-11-21T16:46:02Z")

</div>

The message you’re seeing there is specific to jax. It’s ok to ignore this warning and your model should work just fine on GPU (as it’s using pytorch)