Commit Graph

10 Commits

Author SHA1 Message Date
Jerry Zhang
9ae3d7ca90 [reland][quant][pt2e][xnnpack_quantizer] Add support for mul and mul_relu (#107930) (#107992)
Summary: att

Test Plan: buck2 run executorch/examples/quantization:example -- -m=mv3 --verify

Differential Revision: D48588121

Pull Request resolved: https://github.com/pytorch/pytorch/pull/107992
Approved by: https://github.com/digantdesai, https://github.com/mcr229
2023-08-27 14:50:03 +00:00
PyTorch MergeBot
8d44b0f5a5 Revert "[quant][pt2e][xnnpack_quantizer] Add support for mul and mul_relu (#107930)"
This reverts commit 1d1739dc6d.

Reverted https://github.com/pytorch/pytorch/pull/107930 on behalf of https://github.com/facebook-github-bot due to Diff reverted internally ([comment](https://github.com/pytorch/pytorch/pull/107930#issuecomment-1694069330))
2023-08-26 00:37:02 +00:00
Jerry Zhang
1d1739dc6d [quant][pt2e][xnnpack_quantizer] Add support for mul and mul_relu (#107930)
Summary: att

Test Plan: buck2 run executorch/examples/quantization:example -- -m=mv3 --verify

Differential Revision: D48588121

Pull Request resolved: https://github.com/pytorch/pytorch/pull/107930
Approved by: https://github.com/kimishpatel
2023-08-25 23:36:19 +00:00
Jerry Zhang
28be2c674a [quant][pt2e] Move specific quantizer related things outside of main quant code base (#106806) (#107259)
Summary:

Currently in quantizer/quantize_pt2e we import things from specific quantizers (XNNPACKQuantizer, QuantizationConfig) etc.
this PR removes them so it's clearer that they are not part of the core quantization code base

This PR also removed get_supported_operators from main Quantizer since we haven't seen a clear need for this API

Test Plan:
CIs

Imported from OSS

Differential Revision: D48340367

Pull Request resolved: https://github.com/pytorch/pytorch/pull/107259
Approved by: https://github.com/kimishpatel
2023-08-18 21:29:09 +00:00
Jerry Zhang
4afab40b56 [quant][pt2e] Removed mean/hardtanh annotations and refactored adaptive_avg_pool annotation (#106805)
Summary:
Removed annotations for some ops, since they are handled in torch/ao/quantization/pt2e/_propagate_annotation.py

Test Plan:
CIs

Reviewers:

Subscribers:

Tasks:

Tags:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106805
Approved by: https://github.com/kimishpatel
2023-08-10 04:51:06 +00:00
Jerry Zhang
e1a1780626 [quant][pt2e] Move annotate functions in XNNPACKQuantizer to utils (#106642)
Summary:
This is to allow sharing these annotate functions by other quantizers so that writing a new quantizer is easier

note that these annotation functions will be maintained by XNNPACKQuantizer developers instead of AO team

Test Plan:
python test/test_quantization.py TestQuantizePT2E

Reviewers:

Subscribers:

Tasks:

Tags:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106642
Approved by: https://github.com/andrewor14
2023-08-09 18:52:39 +00:00
Jerry Zhang
d528a137e0 [quant][pt2e][quantizer] Suppoert set_module_type in XNNPACKQuantizer (#106094)
Summary:
Added support to allow users to set configurations based on module type in XNNPACKQuantizer, can also serve as an example
for implementing new quantizers

Test Plan:
python test/test_quantization.py TestQuantizePT2E.test_xnnpack_quantizer_set_module_type

Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106094
Approved by: https://github.com/andrewor14
ghstack dependencies: #106087
2023-08-02 08:33:58 +00:00
Jerry Zhang
92a22a8098 [quant][pt2e][quantizer] Suppoert set_module_name in XNNPACKQuantizer (#106087)
Summary:
Added support to allow users to set configurations based on module name in XNNPACKQuantizer, can also serve as an example
for implementing new quantizers

Test Plan:
python test/test_quantization.py TestQuantizePT2E.test_xnnpack_quantizer_set_module_name

Reviewers:

Subscribers:

Tasks:

Tags:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106087
Approved by: https://github.com/andrewor14
2023-08-02 01:19:23 +00:00
Edward Z. Yang
7b9d250f06 Change _dynamo.export to be export(f)(*args, **kwargs) (#106109)
Signed-off-by: Edward Z. Yang <ezyang@meta.com>

Pull Request resolved: https://github.com/pytorch/pytorch/pull/106109
Approved by: https://github.com/voznesenskym
2023-07-27 21:41:13 +00:00
Jerry Zhang
3a77f9aaaf [quant][api] Move torch.ao.quantization.pt2e.quantizer to torch.ao.quantization.quantizer (#105885)
Summary: moving quantizer to torch.ao.quantization to make it a public api, since pt2e is a folder for implementations

Test Plan:
CIs

sanity check: "buck test //executorch/backends/xnnpack/test:test_xnnpack_quantized_models -- test_resnet18"

Differential Revision: D47727838

Pull Request resolved: https://github.com/pytorch/pytorch/pull/105885
Approved by: https://github.com/andrewor14
2023-07-26 18:20:09 +00:00