Saeid Ghafouri

Thank you @singhniraj08, Is there a same plan on the roadmap for cpu inferencing?

@Miffyli @araffin sure! I will add the PR.

Hi @cliveseldon , is the error related to the commit? Doc tests are causing errors but as far as I understand the commits' changes are not linked to the doc.

Hi @cliveseldon , is the error related to the commit? Doc tests are causing errors but as far as I understand the commits' changes are not linked to the doc.

These are also the results for Seldon with svc and without svc. Might be of interest for further performance optimizations.  

Hey @adriangonz , The main issue is that reloading the model will impose a downtime for changes like change of batch variables which technically do not need the reloading. e.g....

Hey @adriangonz , The model can be re-loaded in the runtime with minimal disruption [using this](https://mlserver.readthedocs.io/en/stable/examples/model-repository/README.html). However, the problem is I couldn't find any way to modify the model setting...

Hi @adriangonz , I'm glad to hear that's something on the agenda. Personally, I think it should be part of the model servers and upsteam frameworks be responsible for high-level...

I'm facing the same issue, did you find any solution for this?

No problem! Glad to be of any help. Sorry, I couldn't find any comments on the pull request. Do you mean this comment on [MobileVit issue](https://github.com/huggingface/peft/issues/1967#issuecomment-2257868726)? If so, the problem...