[Oneshot Refactor] Main refactor

[horheynm]

ORDER OF REVIEWS:

1. [Oneshot Refactor] Rename get_shared_processor_src to get_processor_name_from_model #1108
2. [Oneshot Refactor] dataclass Arguments #1103
3. [Oneshot refactor] Refactor initialize_model_from_path #1109
4. [Oneshot Refactor] Main refactor #1110 <- current PR

SUMMARY:

• Create a class to decouple dependency to main. Class Oneshot consists of pre-processing, carrying out oneshot logic and post-processing
• Move the oneshot class and method under llmcompressor/entrypoints/oneshot.py.
• Add ReadMe in /llmcompressor/entrypoints for info on oneshot
• Delete oneshot logic from /finetune directory, add deprecation warning
• Remove apply used only for stagerunner oneshot pathway in session.py and session_function.py
• Add oneshot only calibration dataloader logic
• Add a return variable of model: PretrainedModel for def oneshot.
• Make oneshot carryout logic independent of TrainingArguments
• remove overwrite_output_dir as oneshot input arg -> only used for TrainingArguments
• Update README on /finetune path. Remove oneshot logic and oneshot with fsdp
• Update wrap_save_pretrained logic to run only if not updated already -> used for stage runner to avoid double wrapping

Entrypoints:

from llmcompressor import oneshot
oneshot(**kwargs) # calls Oneshot

or

from llmcompressor import Oneshot
oneshot = Oneshot(**kwargs)
oneshot() # preprocesss, carries out logic and post process

TEST PLAN:
Pass all tests and examples.
Verified https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py works as expected.

FOLLOW UPS:

• Stage runner removal
• Update entrypoints folder with train, eval, predict, etc.

[github-actions]

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

[dsikka]

Blocked on #1103

SUMMARY:

• Create a class to decouple dependency to main. Class Oneshot consists of pre-processing, carrying out oneshot logic and post-processing

Entrypoints:

oneshot(**kwargs) # calls Oneshot

or

oneshot = Oneshot(**kwargs)
oneshot.run() # preprocesss, carries out logic and post process

TEST PLAN: Contingent on #1103, should pass all tests

Can you update the PR description so it clearly lays out what PRs we should be reviewing and in what order, so that it is easier to understand the changes?

[dsikka]

Have we verified example testing cases? E.g
https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py

[horheynm]

Closing and making changes to
#1136

[horheynm]

Have we verified example testing cases? E.g https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py

Yes!

[brian-dellabetta]

approved with a comment

[kylesayrs]

Good job

[dsikka]

LGTM pending lm_eval testing.
Can confirm performance testing and staged recipes look good.