saymrwulf/pytorch
1
0
Fork 0
mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-15 21:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
pytorch/test/quantization
History
Vasiliy Kuznetsov 3a8752db86 ns for fx: skip shadowing ops if copy subgraph is not implemented (#76663) 
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/76663

Subgraph copy does not handle all edge cases. It's high eng time
to handle them all, and currently an unhandled edge case crashes
the script.

This PR adds a function to check if the subgraph copy is supported,
and skips shadowing if it is not supported. This way the model
can still go through the shadowing APIs without an exception.

Test Plan:
```
python test/test_quantization.py -k FXNumericSuite
```

Reviewed By: hx89

Differential Revision: D36069304

Pulled By: vkuzo

fbshipit-source-id: 6b38b8d8e43396a4cf2373b247223a19d451d096
(cherry picked from commit e2322ca0635c51a4701e60fa90f77915a3c46d0f)
2022-05-05 13:19:53 +00:00
..
ao_migration [quant][fx][improvement] Renamed default_affine_fixed_qparams_observer and default_symmetric_fixed_qparams_observer (#76637) 2022-05-04 02:39:20 +00:00
bc [Quant][fx] Reenable serialization test after convert refactor (#74204) 2022-03-15 03:51:14 +00:00
core [quant][fx][improvement] Renamed default_affine_fixed_qparams_observer and default_symmetric_fixed_qparams_observer (#76637) 2022-05-04 02:39:20 +00:00
dbr dbr quant: enable reference module support for torch.qint32 (#73493) 2022-03-04 17:35:31 +00:00
eager Fix ONNX ATen fallback for non-caffe2 engines 2022-04-14 23:18:45 +00:00
fx ns for fx: skip shadowing ops if copy subgraph is not implemented (#76663) 2022-05-05 13:19:53 +00:00
jit
serialized [Quant][fx] Reenable serialization test after convert refactor (#74204) 2022-03-15 03:51:14 +00:00
__init__.py