Fix (GPxQ): unwrap QuantTensor when dealing with QuantLinear #915
Conversation
This file contains 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
|
Tests are failing. Is this because of the PR? |
fabianandresgrob
force-pushed
the
fix/gpxq-quant-input
branch
from
6e8c7a2
to
e7c54bf
Compare
|
@fabianandresgrob would you mind fixing the error so we can merge this? |
fabianandresgrob
force-pushed
the
fix/gpxq-quant-input
branch
from
e7c54bf
to
3589584
Compare
|
No longer needed. |
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Outdated suggestions cannot be applied.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.
When running GPxQ and we use quantized activations, once a
QuantLinearlayer is processed,update_batchtries to unsqueeze (GPFQ) or transpose (GPTQ) thatQuantTensor, leading to an error.This PR solves that issue by unwrapping that tensor. It also adds a quant linear model in the fixtures for reproducing the issue.
Some of the tests still fail as it does not raise a
ValueErrorbecause it actually has aquant_input(here). @i-colbert maybe we need to change the conditions for an expected fail?