3 Commits

Author	SHA1	Message	Date
Dmytro Dzhulgakov	ebc2365fd3	Serialization for per channel qtensor (#26339) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/26339 Serializes per-channel tensor in both torch.serialization and jit. Since we didn't bind Quantizer properly yet, I chose to save a tuple representing quantizer settings. To avoid recursive tensor serialization calls, I'm using tuple instead of tensor to store scales and zero points. driazati - please check the serialization logic. Is there a good test that compares that JIT serialization and python serialization are equivalent? (I haven't tested it yet) Test Plan: Imported from OSS Differential Revision: D17443222 Pulled By: dzhulgakov fbshipit-source-id: a34758de1ffd2ec1cdc5355f5baf95284a4ccf4b	2019-09-23 13:28:11 -07:00
James Reed	173dc5d16f	__reduce__ for QScheme (#24969) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/24969 This allows pickling qscheme objects Test Plan: Imported from OSS Differential Revision: D16946567 Pulled By: jamesr66a fbshipit-source-id: 57dbedb1e1aca2a2e17916eed662f727053ea926	2019-08-21 19:08:54 -07:00
Jerry Zhang	94f903654c	Add qscheme() method (#20608) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/20608 Exposing QScheme in python as Python objects like `torch.qscheme.per_tensor_affine` etc. Reviewed By: zafartahirov Differential Revision: D15364354 fbshipit-source-id: 4d6a96d67e9ead051cf4a8f934553a8c7232fdb7	2019-06-14 16:29:29 -07:00