[bitsandbytes] Simplify bnb int8 dequant #10401
Open
+3,645
−3,630
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
sayakpaul
commented
Dec 28, 2024
| @@ -205,6 +208,7 @@ def _create_accelerate_new_hook(old_hook): | |||
|
|
|||
| def _dequantize_and_replace( | |||
| model, | |||
| dtype, | |||
There was a problem hiding this comment.
This is a private method so signature modification should be fine.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
akx
reviewed
Jan 2, 2025
matthewdouglas
approved these changes
Jan 6, 2025
|
Cc: @a-r-r-o-w for awareness. |
|
@DN6 this will also fix https://github.com/huggingface/diffusers/actions/runs/12700836694/job/35404284413#step:7:266. Could you take a look? |
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Outdated suggestions cannot be applied.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.
What does this PR do?
With the current code and latest
bitsandbytesinstallation,tests/quantization/bnb/test_mixed_int8.py::SlowBnb8bitTests::test_generate_quality_dequantizewill fail with the following error:Error
Only row-major format inputs are supported, but got format `col32`See internal link: https://huggingface.slack.com/archives/C04NNCRFYUQ/p1735231882230089.
Similar to huggingface/transformers#35068.