Closed shawn-davis closed 4 months ago
Adds the ability to instantiate LLM services/clients dynamically, so that models can be swapped out with command line arguments or config files instead of having to refactor pipeline code. Closes #1630
This pull request requires additional validation before any workflows can run on NVIDIA's runners.
Pull request vetters can view their responsibilities here.
Contributors can view more details about this message here.
/ok to test
Merging to a feature branch to allow additional PRs to be created that fix the tests and documentation
Description
Adds the ability to instantiate LLM services/clients dynamically, so that models can be swapped out with command line arguments or config files instead of having to refactor pipeline code. Closes #1630
By Submitting this PR I confirm: