Skip to content

Conversation

DevinTDHa
Copy link
Member

Description

This PR allows llama.cpp based annotators (AutoGGUF*) to be closed to free up resources.

Motivation and Context

Users might want to test multiple models. This ensures that resources are not used up in the process.

How Has This Been Tested?

Local tests, databricks and colab passing.

@DevinTDHa DevinTDHa added the DON'T MERGE Do not merge this PR label Oct 13, 2025
@DevinTDHa DevinTDHa force-pushed the feature/autogguf-unload branch from d83eefc to cdb131b Compare October 14, 2025 13:18
@DevinTDHa DevinTDHa changed the base branch from master to release/620-release-candidate October 20, 2025 11:00
@DevinTDHa DevinTDHa marked this pull request as ready for review October 20, 2025 11:02
@DevinTDHa DevinTDHa merged commit f36449a into JohnSnowLabs:release/620-release-candidate Oct 20, 2025
4 checks passed
@DevinTDHa DevinTDHa mentioned this pull request Oct 20, 2025
10 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

DON'T MERGE Do not merge this PR

1 participant