[ao][sparsity] make sparsity and PTQ compose #74845

HDCharles · 2022-03-28T18:33:06Z

Stack from ghstack (oldest at bottom):

Summary: This PR adds support for quantization flow to detect
parametrized modules and match them using their original module types.
This mainly involved using the new type_before_parametrizations function rather than
type to check for module mathcing

Test Plan: python test/test_ao_sparsity.py TestComposability

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: D35240274

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

facebook-github-bot · 2022-03-28T18:33:13Z

🔗 Helpful links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/74845
📄 Preview Python docs built from this PR
📄 Preview C++ docs built from this PR
❓Need help or want to give feedback on the CI? Visit our office hours

💊 CI failures summary and remediations

As of commit f25677b (more details on the Dr. CI page):

💚 💚 Looks good so far! There are no failures yet. 💚 💚

This comment was automatically generated by Dr. CI (expand for details).

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using a new nonparam_type function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

torch/ao/quantization/utils.py

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using a new nonparam_type function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

HDCharles · 2022-03-30T03:47:49Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D35240274](https://our.internmc.facebook.com/intern/diff/D35240274) [ghstack-poisoned]

HDCharles · 2022-03-30T15:24:33Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D35240274](https://our.internmc.facebook.com/intern/diff/D35240274) [ghstack-poisoned]

HDCharles · 2022-03-30T16:46:21Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D35240274](https://our.internmc.facebook.com/intern/diff/D35240274) [ghstack-poisoned]

HDCharles · 2022-03-31T18:00:28Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

jerryzh168 · 2022-04-01T21:28:00Z

test/ao/sparsity/test_composability.py

+        self.assertTrue(isinstance(mod[5], torch.nn.quantized.Linear))
+        self.assertEqual(mod(torch.randn(1, 4, 4, 4)).shape, torch.Size([1, 4, 4, 4]))
+
+    def test_s_prep_before_q_prep(self):


nit: maybe we can add a bit more context to this test in docstring about what this is testing

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D35240274](https://our.internmc.facebook.com/intern/diff/D35240274) [ghstack-poisoned]

HDCharles · 2022-04-04T16:17:55Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D35240274](https://our.internmc.facebook.com/intern/diff/D35240274) [ghstack-poisoned]

HDCharles · 2022-04-04T18:05:04Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

HDCharles · 2022-04-04T19:08:40Z

@HDCharles has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: Pull Request resolved: #74845 This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Imported from OSS Reviewed By: jerryzh168 Differential Revision: D35240274 fbshipit-source-id: 7294d89c9c2e069e51d8b9bafa45c15f92bed124

github-actions · 2022-04-05T03:36:10Z

Hey @HDCharles.
You've committed this PR, but it does not have both a 'release notes: ...' and 'topics: ...' label. Please add one of each to the PR. The 'release notes: ...' label should represent the part of PyTorch that this PR changes (fx, autograd, distributed, etc) and the 'topics: ...' label should represent the kind of PR it is (not user facing, new feature, bug fix, perf improvement, etc). The list of valid labels can be found here for the 'release notes: ...' and here for the 'topics: ...'.
For changes that are 'topic: not user facing' there is no need for a release notes label.

Summary: This PR adds support for quantization flow to detect parametrized modules and match them using their original module types. This mainly involved using the new type_before_parametrizations function rather than type to check for module mathcing Test Plan: python test/test_ao_sparsity.py TestComposability Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: deff7a8 Pull Request resolved: pytorch/pytorch#74845

facebook-github-bot added the cla signed label Mar 28, 2022

This was referenced Mar 28, 2022

[ao][sparsity] make sparsity compose with PTQ convert #74846

Closed

[ao][sparsity] Composability of fusion and sparsity #74847

Closed

[ao][sparsity] comsability for sparsity and QAT convert #74848

Closed

HDCharles requested a review from z-a-f March 28, 2022 18:48

HDCharles added 2 commits March 28, 2022 16:08

HDCharles changed the title ~~Make quantization work with sparsity parametrizations~~ [ao][sparsity] make sparsity and PTQ compose Mar 28, 2022

HDCharles added 3 commits March 28, 2022 16:45

HDCharles requested review from andrewor14, dzdang, jerryzh168, terrychenism and vkuzo and removed request for z-a-f March 28, 2022 23:51

vkuzo reviewed Mar 29, 2022

View reviewed changes

torch/ao/quantization/utils.py Outdated Show resolved Hide resolved

vkuzo reviewed Mar 29, 2022

View reviewed changes

torch/ao/quantization/utils.py Outdated Show resolved Hide resolved

HDCharles added 3 commits March 28, 2022 19:00

jerryzh168 reviewed Apr 1, 2022

View reviewed changes

jerryzh168 approved these changes Apr 1, 2022

View reviewed changes

HDCharles requested a review from lezcano as a code owner April 4, 2022 16:12

lezcano removed their request for review April 4, 2022 20:06

pytorchmergebot closed this in 02e30a0 Apr 5, 2022

facebook-github-bot deleted the gh/HDCharles/62/head branch April 8, 2022 14:17

WBobby mentioned this pull request Aug 17, 2022

Add ROCm5.2.3/AMDGPU support for PyTorch WBobby/pytorch#2

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[ao][sparsity] make sparsity and PTQ compose #74845

[ao][sparsity] make sparsity and PTQ compose #74845

Uh oh!

HDCharles commented Mar 28, 2022 •

edited

Loading

Uh oh!

facebook-github-bot commented Mar 28, 2022 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

HDCharles commented Mar 30, 2022

Uh oh!

HDCharles commented Mar 30, 2022

Uh oh!

HDCharles commented Mar 30, 2022

Uh oh!

HDCharles commented Mar 31, 2022

Uh oh!

jerryzh168 Apr 1, 2022

Uh oh!

HDCharles commented Apr 4, 2022

Uh oh!

HDCharles commented Apr 4, 2022

Uh oh!

HDCharles commented Apr 4, 2022

Uh oh!

github-actions bot commented Apr 5, 2022

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

[ao][sparsity] make sparsity and PTQ compose #74845

[ao][sparsity] make sparsity and PTQ compose #74845

Uh oh!

Conversation

HDCharles commented Mar 28, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

facebook-github-bot commented Mar 28, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful links

💊 CI failures summary and remediations

Uh oh!

Uh oh!

Uh oh!

HDCharles commented Mar 30, 2022

Uh oh!

HDCharles commented Mar 30, 2022

Uh oh!

HDCharles commented Mar 30, 2022

Uh oh!

HDCharles commented Mar 31, 2022

Uh oh!

jerryzh168 Apr 1, 2022

Choose a reason for hiding this comment

Uh oh!

HDCharles commented Apr 4, 2022

Uh oh!

HDCharles commented Apr 4, 2022

Uh oh!

HDCharles commented Apr 4, 2022

Uh oh!

github-actions bot commented Apr 5, 2022

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

HDCharles commented Mar 28, 2022 •

edited

Loading

facebook-github-bot commented Mar 28, 2022 •

edited

Loading