pytorch/test/quantization
andrewor14 e7dd9b1138 [Quant][test] Add test for mixed dtypes in the same model (#96104)
Summary: This commit adds a test for mixing multiple dtypes
for different layers in the same model. The test verifies that
FX graph mode quantization converts the dtypes correctly
between the layers.

Test Plan:
python test/test_quantization.py TestQuantizeFx.test_mixed_dtypes

Reviewers: jcaip, vkuzo, supriyar

Subscribers: jcaip, vkuzo, supriyar
Pull Request resolved: https://github.com/pytorch/pytorch/pull/96104
Approved by: https://github.com/jcaip
2023-03-08 17:08:12 +00:00
..
ao_migration ao migration: remove package test as this behavior is tested by other things (#94422) 2023-02-13 16:33:40 +00:00
bc [BE] [3/3] Rewrite super() calls in test (#94592) 2023-02-12 22:20:53 +00:00
core Add various uninterpreted bit tensor data types (try 2) (#95860) 2023-03-04 03:35:59 +00:00
eager [BE] [3/3] Rewrite super() calls in test (#94592) 2023-02-12 22:20:53 +00:00
fx [Quant][test] Add test for mixed dtypes in the same model (#96104) 2023-03-08 17:08:12 +00:00
jit [BE] [3/3] Rewrite super() calls in test (#94592) 2023-02-12 22:20:53 +00:00
serialized
__init__.py