Compressed tensors fp8#47216
Open
SunMarc wants to merge 60 commits into
Open
Conversation
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Co-authored-by: Steven Liu <[email protected]>
Co-authored-by: Steven Liu <[email protected]>
Co-authored-by: Steven Liu <[email protected]>
Co-authored-by: Steven Liu <[email protected]>
Co-authored-by: Steven Liu <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
Signed-off-by: jiqing-feng <[email protected]>
# Conflicts: # src/transformers/quantizers/quantizer_compressed_tensors.py
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: compressed_tensors_integration |
SunMarc
commented
Jul 9, 2026
Comment on lines
-110
to
-124
| # assume that if `hasattr(self, hf_quantizer)` and `has_moe_conversion(self)` and `is_moe_proj_in_config_scheme` | ||
| # then it needs special dequantization for MoE projections | ||
| # NOTE: MoE conversion should happen AFTER decompression! Already hardcoded in conversion | ||
| dequant_conversions = [ | ||
| WeightConverter( | ||
| source_patterns=[ | ||
| r".weight_packed$", | ||
| r".weight_scale$", | ||
| r".weight_shape$", | ||
| ], | ||
| target_patterns=r"weight", | ||
| operations=[DecompressExperts(self)], | ||
| ), | ||
| ] | ||
| return dequant_conversions |
Member
Author
There was a problem hiding this comment.
I don't think we need that no @zucchini-nlp ? like in any case the moe from compressed tensors will be split and we have to fuse them nevertheless in update_weight_conversions. Hence, I prefer to remove it if this is not needed for now.
|
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. |
Contributor
CI recapDashboard: View test results in Grafana |
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
3 participants
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?
Supersedes #45699
cc @jiqing-feng if you can have a look at