Merged
Conversation
|
👋 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. |
brian-dellabetta
commented
Mar 4, 2025
dsikka
previously approved these changes
Mar 4, 2025
87dcc4c to
1f2ce00
Compare
dsikka
requested changes
Mar 5, 2025
3429cc7 to
b91cd7b
Compare
horheynm
previously approved these changes
Mar 7, 2025
2d2e220
b91cd7b to
2d2e220
Compare
kylesayrs
previously approved these changes
Mar 7, 2025
SUMMARY: Fixed logging and clear loggers enabling/disabling bug. Previously, any value on the right environment variables would disable logging. Now, we explicitly check for `true` TEST PLAN: Added unit tests for enabling logging. `make test` passes --------- Signed-off-by: Aman Gupta <aman2304@gmail.com> Co-authored-by: Dipika Sikka <dipikasikka1@gmail.com> Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
…ot (#1212) Order of reviews: #1206 #1207 #1209 #1212 <-- Here #1214 SUMMARY: * Move the preprocessing and postprocessing logic out of `src/llmcompressor/transformers/finetune/text_generation.py` and into `src/llmcompressor/entrypoints/utils.py` TEST PLAN: Pass tests Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
SUMMARY: Current README shows which algo we support + how to run. However, to a user it is still hard to understand when to use which. Add more info on based on the users use-case and hardware the optimization to apply. TEST PLAN: N/A Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
## Purpose ## * Simplify the modifier lifecycle by removing the ability for modifiers to affect the model after the modifier's `end` event * This allows the `on_event` method to be removed in a future change ## Background ## * The `leave_enabled` option was originally intended as a shortcut to simplify recipes which used magnitude pruning during the iterative pruning, then needed the masks to stay enabled during stabilization SFT * This change proposes making the recipe clearer by requiring the ConstantPruningModifier after the MagnitudePruningModifier becomes inactive ## Changes ## * Remove `MagnitudePruningModifier.leave_enabled` with a deprecation warning Signed-off-by: Kyle Sayers <kylesayrs@gmail.com> Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
Co-authored-by: Kyle Sayers <kylesayrs@gmail.com> Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
## Purpose ## * Fix tests which break as a result of https://github.com/vllm-project/llm-compressor/pull/new/kylesayrs/replace-self-hosted ## Changes ## * Use self-hosted model stub Signed-off-by: Kyle Sayers <kylesayrs@gmail.com> Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
fffabf0 to
341299f
Compare
dsikka
approved these changes
Mar 11, 2025
kylesayrs
approved these changes
Mar 11, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
SUMMARY:
LM Eval weekly tests are failing, this resolves two issues
TEST PLAN:
no new src code