bugfix: inference mode context for example notebooks

[TaplierShiru]

Fix issue regarding OutOfMemoryError which occur for me in sam3_image_batched_inference.ipynb notebook.
Simple fix is to keep context as global variable.

Also strange that similar thing but for autocast:

# use bfloat16 for the entire notebook. If your card doesn't support it, try float16 instead
torch.autocast("cuda", dtype=torch.bfloat16).__enter__()

Actually works as intended regardless of whether the context has been preserved or not. I checked it via:

# Check if autocast is active
print(torch.is_autocast_enabled('cuda')) 

# Check the autocast dtype
print(torch.get_autocast_dtype('cuda')) 

In order to be more consistent - maybe add similar thing for autocast?

Also someone mention about high memory consumption while process video (comment), but looking at the example notebook sam3_video_predictor_example.ipynb (I also run notebook with\without inference mode as global - there is no difference) - I think such error not occur there, only if user use model without any wrappers.

[meta-cla]

Hi @TaplierShiru!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[meta-cla]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!