Fix BertSdpaSelfAttention quantization #648
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
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
kinjalpatel27
force-pushed
the
kinjal/int8_quant
branch
from
9b97f1b to
39b3cc7
Compare
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #648 +/- ##
=======================================
Coverage 74.68% 74.68%
=======================================
Files 183 183
Lines 18552 18552
=======================================
Hits 13856 13856
Misses 4696 4696 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
realAsma
approved these changes
Dec 4, 2025
kevalmorabia97
pushed a commit
that referenced
this pull request
Dec 7, 2025
## What does this PR do?
**Type of change:** Bug fix
**Overview:**
`BertSDPASelfAttention` quantization was failing
Issue: Decorators (e.g., @deprecate_kwarg in BERT) wrap methods and
change their free variables. The modified AST needs __class__ for
super(), but the decorated wrapper has different freevars (e.g.,
'additional_message', 'func').
Fix: Search the decorator's closure to find the actual undecorated
method with matching free variables, then use its globals and closure
for bytecode reconstruction.
## Usage
```
cd examples/chained_optimizations
bash scripts/1_prune.sh
bash scripts/2_int8_quantize.sh
```
## Testing
Added unit test: test_kv_quant_bert
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
NA
## Additional Information
<!-- E.g. related issue. -->
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
soodoshll
pushed a commit
to soodoshll/TensorRT-Model-Optimizer
that referenced
this pull request
Dec 8, 2025
## What does this PR do?
**Type of change:** Bug fix
**Overview:**
`BertSDPASelfAttention` quantization was failing
Issue: Decorators (e.g., @deprecate_kwarg in BERT) wrap methods and
change their free variables. The modified AST needs __class__ for
super(), but the decorated wrapper has different freevars (e.g.,
'additional_message', 'func').
Fix: Search the decorator's closure to find the actual undecorated
method with matching free variables, then use its globals and closure
for bytecode reconstruction.
## Usage
```
cd examples/chained_optimizations
bash scripts/1_prune.sh
bash scripts/2_int8_quantize.sh
```
## Testing
Added unit test: test_kv_quant_bert
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
NA
## Additional Information
<!-- E.g. related issue. -->
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
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?
Type of change: Bug fix
Overview:
BertSDPASelfAttentionquantization was failingIssue: Decorators (e.g., @deprecate_kwarg in BERT) wrap methods and change their free variables. The modified AST needs class for super(), but the decorated wrapper has different freevars (e.g., 'additional_message', 'func').
Fix: Search the decorator's closure to find the actual undecorated method with matching free variables, then use its globals and closure for bytecode reconstruction.
Usage
Testing
Added unit test: test_kv_quant_bert
Before your PR is "Ready for review"
Additional Information