Commit Graph

8 Commits

Author SHA1 Message Date
Jerry Zhang
f575df201f [quant][graphmode][jit][api] Expose preserved_attrs from finalize to convert_jit (#44490)
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/44490

Test Plan: Imported from OSS

Reviewed By: z-a-f

Differential Revision: D23631142

fbshipit-source-id: f0913f0cb4576067e2a7288326024942d12e0ae0
2020-09-22 19:37:25 -07:00
Xiang Gao
20ac736200 Remove py2 compatible future imports (#44735)
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/44735

Reviewed By: mruberry

Differential Revision: D23731306

Pulled By: ezyang

fbshipit-source-id: 0ba009a99e475ddbe22981be8ac636f8a1c8b02f
2020-09-16 12:55:57 -07:00
Jerry Zhang
7db7da7151 [reland][quant][graphmode][fx] Add top level APIs (#43581) (#43901)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43901

Add similar APIs like eager and graph mode on torchscript
- fuse_fx
- quantize_fx (for both post training static and qat)
- quantize_dynamic_fx (for post training dynamic)
- prepare_fx (for both post training static and qat)
- prepare_dynamic_fx (for post training dynamic)
- convert_fx (for all modes)

Test Plan:
Imported from OSS

Imported from OSS

Reviewed By: vkuzo

Differential Revision: D23432430

fbshipit-source-id: fc99eb75cbecd6ee7a3aa6c8ec71cd499ff7e3c1
2020-08-31 18:24:26 -07:00
Alban Desmaison
f7bae5b6b1 Revert D23385091: [quant][graphmode][fx] Add top level APIs
Test Plan: revert-hammer

Differential Revision:
D23385091 (eb4199b0a7)

Original commit changeset: b789e54e1a0f

fbshipit-source-id: dc3dd9169d34beab92488d78d42d7e7d05e771d1
2020-08-31 12:18:29 -07:00
Jerry Zhang
eb4199b0a7 [quant][graphmode][fx] Add top level APIs (#43581)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43581

Add similar APIs like eager and graph mode on torchscript
- fuse_fx
- quantize_fx (for both post training static and qat)
- quantize_dynamic_fx (for post training dynamic)
- prepare_fx (for both post training static and qat)
- prepare_dynamic_fx (for post training dynamic)
- convert_fx (for all modes)

Test Plan: Imported from OSS

Reviewed By: vkuzo

Differential Revision: D23385091

fbshipit-source-id: b789e54e1a0f3af6b026fd568281984e253e0433
2020-08-31 10:12:55 -07:00
Jerry Zhang
0e26a03ef9 [quant][graphmode] Enable inplace option for top level API (#40414)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40414

after `_reconstruct` is supported in RecursiveScriptModule: https://github.com/pytorch/pytorch/pull/39979
we can support inplace option in quantization API

Test Plan: Imported from OSS

Differential Revision: D22178326

fbshipit-source-id: c78bc2bcf2c42b06280c12262bb31aebcadc6c32
2020-06-23 16:42:48 -07:00
Jerry Zhang
59ca1d31ca [quant][graphmode] docstrings for top level APIs (#40328)
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/40328

Test Plan: Imported from OSS

Differential Revision: D22149708

fbshipit-source-id: 63a1cd229d9e4668fba0ef3977e894cb8984318b
2020-06-19 22:20:23 -07:00
Jerry Zhang
b2f489dc57 [quant][graphmode] Rename graph mode quantization API to quantize_jit (#40212)
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/40212

Test Plan: Imported from OSS

Reviewed By: z-a-f

Differential Revision: D22144745

fbshipit-source-id: 38a19b5afdddbbce262eea8ddf5b68458e6017b3
2020-06-19 18:13:37 -07:00