pytorch/test/quantization
Wanchao Liang a9e7e787f8 [jit] make clone works for interface type (#42121)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/42121

This PR changes the Module API to allow register a module with module
interface type, and therefore allows Module::clone works on the case
where there's a module interface type being shared by two submodules.

interface type will be shared by the new cloned instance in the same
compilation unit bc it only
contains a list of functionSchema, which does not involve any
attributes compared to classType.

fixes https://github.com/pytorch/pytorch/issues/41882

Test Plan: Imported from OSS

Reviewed By: suo

Differential Revision: D22781205

Pulled By: wanchaol

fbshipit-source-id: f97f4b75970f0b434e38b5a1f778eda2c4e5109b
2020-07-31 10:24:27 -07:00
..
serialized
__init__.py remediation of S205607 2020-07-17 17:19:47 -07:00
test_backward_compatibility.py
test_equalize.py cross_layer_equalization (#41685) 2020-07-22 08:39:23 -07:00
test_fusion_passes.py
test_numeric_suite.py [quant][refactor] test_only_eval_fn (#41078) 2020-07-09 12:34:05 -07:00
test_qat_module.py
test_quantize.py Move qconfig removal into convert() (#41930) 2020-07-25 13:27:13 -07:00
test_quantize_jit.py [jit] make clone works for interface type (#42121) 2020-07-31 10:24:27 -07:00
test_quantized_functional.py
test_quantized_module.py [quant][refactor] test_only_eval_fn (#41078) 2020-07-09 12:34:05 -07:00
test_quantized_op.py Change whitelist to allow in file test_quantized_op.py (#41771) 2020-07-21 11:08:07 -07:00
test_quantized_tensor.py quantizer.cpp: fix cuda memory pinning (#41139) 2020-07-09 11:14:58 -07:00
test_workflow_module.py Updates to Scale and Zero Point Gradient Calculation (#42034) 2020-07-27 11:18:49 -07:00