# Llava endpoint on Sagemaker

**URL:** <https://discuss.huggingface.co/t/llava-endpoint-on-sagemaker/86124>\
**Category:** Amazon SageMaker\
**Created:** [May 10, 2024, 1:04pm UTC](https://discuss.huggingface.co/t/llava-endpoint-on-sagemaker/86124 "2024-05-10T13:04:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![pj3300](https://avatars.discourse-cdn.com/v4/letter/p/839c29/32.png) [@pj3300](https://discuss.huggingface.co/u/pj3300)\
**Post date:** [May 10, 2024, 1:04pm UTC](https://discuss.huggingface.co/t/llava-endpoint-on-sagemaker/86124/1 "2024-05-10T13:04:08Z")

</div>

Hello everyone,  
I have been trying to delpoy anymodality/llava-v1.5-7b on sagemaker as shown in the noteboko found here [deploy\_llava.ipynb · anymodality/llava-v1.5-7b at main](https://huggingface.co/anymodality/llava-v1.5-7b/blob/main/deploy_llava.ipynb).  
The model is deployed howver, i get an error whenever i perform inference.  
I have been trying and searching a lot but still the same error.  
Here is what i get:

**ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{ “code”: 400, “type”: “InternalServerException”, “message”: “GET was unable to find an engine to execute this computation” }**