projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1b5b210) | patch
[quant][fix] Fix quantization for sub_scalar (#64603)
authorJerry Zhang <jerryzh@fb.com>
Fri, 10 Sep 2021 00:17:01 +0000 (17:17 -0700)
committerFacebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
Fri, 10 Sep 2021 00:18:31 +0000 (17:18 -0700)
commitef2c9d7d8a0b7dbeae36a15d6758ddb75ef02b64
treebda56e8856e65114b17e0de2f4386d95ab81010ftree | snapshot
parent1b5b210f2cc7f54de11dd17d36ef34549b08b3efcommit | diff
[quant][fix] Fix quantization for sub_scalar (#64603)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64603

We'll insert observer only when both the operator and dtype is supported

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

Imported from OSS

Reviewed By: vkuzo

Differential Revision: D30797025

fbshipit-source-id: a77c21e2749405534fc245374cf33a0657a3d2c8
test/quantization/fx/test_quantize_fx.py diff | blob | history
torch/quantization/fx/quantization_patterns.py diff | blob | history
Domain: Machine Learning / ML Framework;