What does this PR do ?

This PR makes the following quality-of-life improvements to inference:

• Removes InferenceWrapperConfig.
• Consolidates all the redundant TransformerConfig arguments in DynamicInferenceContext into a single model_config argument.
• Adds an InferenceConfig object that has all the inference-related configuration parameters from the command line arguments.
• Adds megatron/inference as a location for convenience functions to initialize an InferenceConfig or DynamicInferenceEngine using the global args.
• Updates all driver scripts to use these convenience functions.
• Moves some commonly used utility functions out of gpt_dynamic_inference.py into megatron/inference/utils.py.
• Deprecates the pipeline_parallel_large_batch function in AbstractModelInferenceWrapper
• Removes simple_text_generation_controller.py
• Ensures that the static engine generate function always returns InferenceRequest objects instead of DynamicInferenceRequestRecord objects.

Contribution process

flowchart LR
    A[Pre-checks] --> B[PR Tests]
    subgraph Code Review/Approval
        C1[Expert Review] --> C2[Final Review]
    end
    B --> C1
    C2 --> D[Merge]

Pre-checks

• I want this PR in a versioned release and have added the appropriate Milestone (e.g., Core 0.8)
• I have added relevant unit tests
• I have added relevant functional tests
• I have added proper typing to my code Typing guidelines
• I have added relevant documentation
• I have run the autoformatter.sh on my PR

Code review

The following process is enforced via the CODEOWNERS file for changes into megatron/core. For changes outside of megatron/core, it is up to the PR author whether or not to tag the Final Reviewer team.

Merging your PR

Any member of core-adlr and core-nemo will be able to merge your PR.