mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-12 02:06:41 +08:00
kinjalpatel27
3ef9e395f7
## 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>