topic Maximum wait time Databricks Model Serving in Machine Learning

Maximum wait time Databricks Model Serving

TinSlim — Mon, 09 Dec 2024 19:18:42 GMT

hi, hope you are fine
I deployed a model 3 or 2 months ago using Databricks Serving and MLFlow. The model worked good using GPU from model serving.

I stopped using it for some months and when I tried again deploying it, it has some errors.

1. [FIXED] A dependency error because it was changed since that time, I added this dependency and fixed it:
huggingface_hub==0.23.2

2. When i'm deploying it i get this error and it stops the deploy and update:
An error occurred while loading the model: Exceeded maximum wait time of 300 seconds to load the model

I ask, is there an environment variable to change the timeout of 300 seconds?, I tried adding these variables:

Thanks!

Re: Maximum wait time Databricks Model Serving

Alberto_Umana — Tue, 10 Dec 2024 00:37:10 GMT

Hi @TinSlim,

There looks to be an issue introducing the timeout of the model. What is the name of the model and the cloud region where it was deployed to validate our backend logs?

Re: Maximum wait time Databricks Model Serving

TinSlim — Tue, 10 Dec 2024 02:24:04 GMT

Hi @Alberto_Umana, thanks,

I sent you the information via message

Re: Maximum wait time Databricks Model Serving

Alberto_Umana — Tue, 10 Dec 2024 19:44:59 GMT

Thanks, I will review it and get back. I'll DIM you.