Fix Weekly Test Failure #8
Merged
Conversation
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
bfineran
approved these changes
Jun 25, 2024
dsikka
requested changes
Jun 25, 2024
Sure, how would I test that? Right now I'm just setting |
dbogunowicz
approved these changes
Jun 27, 2024
markmc
pushed a commit
to markmc/llm-compressor
that referenced
this pull request
Nov 13, 2024
gradients shouldn't be computed for Q/DQ in QAT
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Outdated suggestions cannot be applied.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.
Original failure was from sparseml: https://github.com/neuralmagic/sparseml/actions/runs/9636050064/job/26573555739
Issue was that when doing sparsity -> quantization, the quantization modifier needs to be included before SparseGPT. After restructuring the recipe the test passes locally for the 7b model. Also updating the device argument to be "auto" for all models