quant: make various configs printable #91419

vkuzo · 2022-12-27T22:37:33Z

Stack from ghstack (oldest at bottom):

-> quant: make various configs printable #91419

Summary:

Makes various quantization configs print out human readable values instead
of just the class name. This is useful when printing these configs out when
debugging.

Test plan:

test script

conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig()
print(conf_1)

conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig()
print(conf_2)

conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig()
print(conf_3)

conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\
    .set_input_quantized_indexes([0])
print(conf_4)

conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\
    .set_preserved_attributes(['foo'])
print(conf_5)

conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\
    .set_preserved_attributes(['foo'])
print(conf_6)

test script output

DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_
upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa
ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant
_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin
t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None,
quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero
_point_exact_match=None), bias_dtype=None, is_dynamic=None)
BackendConfig({'name': '', '_pattern_complex_format_to_config': {}})
BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>})
PrepareCustomConfig({'input_quantized_indexes': [0]})
ConvertCustomConfig({'preserved_attributes': ['foo']})
FuseCustomConfig({'preserved_attributes': ['foo']})

Summary: Makes various quantization configs print out human readable values instead of just the class name. This is useful when printing these configs out when debugging. Test plan: test script ``` conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig() print(conf_1) conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig() print(conf_2) conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig() print(conf_3) conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\ .set_input_quantized_indexes([0]) print(conf_4) conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_5) conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_6) ``` test script output ``` DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_ upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant _max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero _point_exact_match=None), bias_dtype=None, is_dynamic=None) BackendConfig({'name': '', '_pattern_complex_format_to_config': {}}) BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>}) PrepareCustomConfig({'input_quantized_indexes': [0]}) ConvertCustomConfig({'preserved_attributes': ['foo']}) FuseCustomConfig({'preserved_attributes': ['foo']}) ``` [ghstack-poisoned]

linux-foundation-easycla · 2022-12-27T22:37:35Z

The committers listed above are authorized under a signed CLA.

✅ login: vkuzo / name: Vasiliy Kuznetsov (af6552b, 58b330e, b4311a8)

pytorch-bot · 2022-12-27T22:37:36Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/91419

📄 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 the bot commands wiki or our office hours

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit b4311a8:
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

Summary: Makes various quantization configs print out human readable values instead of just the class name. This is useful when printing these configs out when debugging. Test plan: test script ``` conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig() print(conf_1) conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig() print(conf_2) conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig() print(conf_3) conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\ .set_input_quantized_indexes([0]) print(conf_4) conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_5) conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_6) ``` test script output ``` DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_ upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant _max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero _point_exact_match=None), bias_dtype=None, is_dynamic=None) BackendConfig({'name': '', '_pattern_complex_format_to_config': {}}) BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>}) PrepareCustomConfig({'input_quantized_indexes': [0]}) ConvertCustomConfig({'preserved_attributes': ['foo']}) FuseCustomConfig({'preserved_attributes': ['foo']}) ``` ghstack-source-id: 6acbd915298aee7fac7a8131508ed49c8930aa61 Pull Request resolved: #91419

andrewor14

Thanks! Can be a future PR but it would be good to print different fields on separate lines with the right indentations too; right now the built-in backend configs are printed as a huge jumble of text.

vkuzo · 2023-01-03T17:49:13Z

@pytorchbot help

pytorch-bot · 2023-01-03T17:49:14Z

❌ 🤖 pytorchbot command failed:

@pytorchbot: error: argument command: invalid choice: 'help' (choose from 'merge', 'revert', 'rebase', 'label', 'drci')

usage: @pytorchbot [-h] {merge,revert,rebase,label,drci} ...

Try @pytorchbot --help for more info.

vkuzo · 2023-01-03T17:49:24Z

@pytorchbot --help

pytorch-bot · 2023-01-03T17:49:26Z

PyTorchBot Help

usage: @pytorchbot [-h] {merge,revert,rebase,label,drci} ...

In order to invoke the bot on your PR, include a line that starts with
@pytorchbot anywhere in a comment. That line will form the command; no
multi-line commands are allowed. 

Example:
    Some extra context, blah blah, wow this PR looks awesome

    @pytorchbot merge

optional arguments:
  -h, --help            Show this help message and exit.

command:
  {merge,revert,rebase,label,drci}
    merge               Merge a PR
    revert              Revert a PR
    rebase              Rebase a PR
    label               Add label to a PR
    drci                Update Dr. CI

Merge

usage: @pytorchbot merge [-g | -f MESSAGE | -l] [-r [{viable/strict,master}]]

Merge an accepted PR, subject to the rules in .github/merge_rules.json.
By default, this will wait for all required checks (lint, pull) to succeed before merging.

optional arguments:
  -g, --green           Merge when all status checks running on the PR pass. To add status checks, use labels like `ciflow/trunk`.
  -f MESSAGE, --force MESSAGE
                        Merge without checking anything. This requires a reason for auditting purpose, for example:
                        @pytorchbot merge -f 'Minor update to fix lint. Expecting all PR tests to pass'
  -l, --land-checks     [Deprecated - your PR instead now gets the `ciflow/trunk` label on approval] Merge with land time checks. This will create a new branch with your changes rebased on viable/strict and run a majority of trunk tests _before_ landing to increase trunk reliability and decrease risk of revert. The tests added are: pull, Lint and trunk. Note that periodic is excluded.
  -r [{viable/strict,master}], --rebase [{viable/strict,master}]
                        Rebase the PR to re run checks before merging.  Accepts viable/strict or master as branch options and will default to viable/strict if not specified.

Revert

usage: @pytorchbot revert -m MESSAGE -c
                          {nosignal,ignoredsignal,landrace,weird,ghfirst}

Revert a merged PR. This requires that you are a Meta employee.

Example:
  @pytorchbot revert -m="This is breaking tests on trunk. hud.pytorch.org/" -c=nosignal

optional arguments:
  -m MESSAGE, --message MESSAGE
                        The reason you are reverting, will be put in the commit message. Must be longer than 3 words.
  -c {nosignal,ignoredsignal,landrace,weird,ghfirst}, --classification {nosignal,ignoredsignal,landrace,weird,ghfirst}
                        A machine-friendly classification of the revert reason.

Rebase

usage: @pytorchbot rebase [-s | -b BRANCH]

Rebase a PR. Rebasing defaults to the stable viable/strict branch of pytorch.
You must have write permissions to the repo to rebase a PR.

optional arguments:
  -s, --stable          [DEPRECATED] Rebase onto viable/strict
  -b BRANCH, --branch BRANCH
                        Branch you would like to rebase to

Label

usage: @pytorchbot label labels [labels ...]

Adds label to a PR

positional arguments:
  labels  Labels to add to given Pull Request

Dr CI

usage: @pytorchbot drci

Update Dr. CI. Updates the Dr. CI comment on the PR in case it's gotten out of sync with actual CI results.

vkuzo · 2023-01-03T17:50:15Z

@pytorchbot rebase

pytorchmergebot · 2023-01-03T17:52:57Z

@pytorchbot successfully started a rebase job. Check the current status here

Summary: Makes various quantization configs print out human readable values instead of just the class name. This is useful when printing these configs out when debugging. Test plan: test script ``` conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig() print(conf_1) conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig() print(conf_2) conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig() print(conf_3) conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\ .set_input_quantized_indexes([0]) print(conf_4) conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_5) conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_6) ``` test script output ``` DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_ upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant _max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero _point_exact_match=None), bias_dtype=None, is_dynamic=None) BackendConfig({'name': '', '_pattern_complex_format_to_config': {}}) BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>}) PrepareCustomConfig({'input_quantized_indexes': [0]}) ConvertCustomConfig({'preserved_attributes': ['foo']}) FuseCustomConfig({'preserved_attributes': ['foo']}) ``` [ghstack-poisoned]

pytorchmergebot · 2023-01-03T17:53:18Z

Successfully rebased gh/vkuzo/524/orig onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via ghstack checkout https://github.com/pytorch/pytorch/pull/91419)

Summary: Makes various quantization configs print out human readable values instead of just the class name. This is useful when printing these configs out when debugging. Test plan: test script ``` conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig() print(conf_1) conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig() print(conf_2) conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig() print(conf_3) conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\ .set_input_quantized_indexes([0]) print(conf_4) conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_5) conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_6) ``` test script output ``` DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_ upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant _max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero _point_exact_match=None), bias_dtype=None, is_dynamic=None) BackendConfig({'name': '', '_pattern_complex_format_to_config': {}}) BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>}) PrepareCustomConfig({'input_quantized_indexes': [0]}) ConvertCustomConfig({'preserved_attributes': ['foo']}) FuseCustomConfig({'preserved_attributes': ['foo']}) ``` ghstack-source-id: 0183772b2b42699ba153f2206bb5c0cf053151bd Pull Request resolved: #91419

vkuzo · 2023-01-03T22:06:20Z

@pytorchbot merge

pytorchmergebot · 2023-01-03T22:10:19Z

Merge failed

Reason: The following mandatory check(s) failed (Rule superuser):

EasyCLA

Dig deeper by viewing the failures on hud

Details for Dev Infra team

Raised by workflow job

clee2000 · 2023-01-04T00:42:18Z

/easycla

vkuzo · 2023-01-04T01:09:18Z

@pytorchbot rebase

pytorchmergebot · 2023-01-04T01:11:28Z

@pytorchbot successfully started a rebase job. Check the current status here

Summary: Makes various quantization configs print out human readable values instead of just the class name. This is useful when printing these configs out when debugging. Test plan: test script ``` conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig() print(conf_1) conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig() print(conf_2) conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig() print(conf_3) conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\ .set_input_quantized_indexes([0]) print(conf_4) conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_5) conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_6) ``` test script output ``` DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_ upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant _max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero _point_exact_match=None), bias_dtype=None, is_dynamic=None) BackendConfig({'name': '', '_pattern_complex_format_to_config': {}}) BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>}) PrepareCustomConfig({'input_quantized_indexes': [0]}) ConvertCustomConfig({'preserved_attributes': ['foo']}) FuseCustomConfig({'preserved_attributes': ['foo']}) ``` [ghstack-poisoned]

pytorchmergebot · 2023-01-04T01:11:47Z

Successfully rebased gh/vkuzo/524/orig onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via ghstack checkout https://github.com/pytorch/pytorch/pull/91419)

Summary: Makes various quantization configs print out human readable values instead of just the class name. This is useful when printing these configs out when debugging. Test plan: test script ``` conf_1 = torch.ao.quantization.backend_config.backend_config.DTypeConfig() print(conf_1) conf_2 = torch.ao.quantization.backend_config.backend_config.BackendConfig() print(conf_2) conf_3 = torch.ao.quantization.backend_config.backend_config.BackendPatternConfig() print(conf_3) conf_4 = torch.ao.quantization.fx.custom_config.PrepareCustomConfig()\ .set_input_quantized_indexes([0]) print(conf_4) conf_5 = torch.ao.quantization.fx.custom_config.ConvertCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_5) conf_6 = torch.ao.quantization.fx.custom_config.FuseCustomConfig()\ .set_preserved_attributes(['foo']) print(conf_6) ``` test script output ``` DTypeConfig(input_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_ upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_point_exa ct_match=None), output_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant _max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero_poin t_exact_match=None), weight_dtype_with_constraints=DTypeWithConstraints(dtype=None, quant_min_lower_bound=None, quant_max_upper_bound=None, scale_min_lower_bound=None, scale_max_upper_bound=None, scale_exact_match=None, zero _point_exact_match=None), bias_dtype=None, is_dynamic=None) BackendConfig({'name': '', '_pattern_complex_format_to_config': {}}) BackendPatternConfig({'observation_type': <ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT: 0>}) PrepareCustomConfig({'input_quantized_indexes': [0]}) ConvertCustomConfig({'preserved_attributes': ['foo']}) FuseCustomConfig({'preserved_attributes': ['foo']}) ``` ghstack-source-id: 3269a2431edf0b90f3f7042f73be3f469c356aae Pull Request resolved: #91419

vkuzo · 2023-01-04T01:28:57Z

@pytorchbot merge -g

pytorchmergebot · 2023-01-04T01:30:31Z

Merge started

Your change will be merged once all checks on your PR pass since you used the green (-g) flag (ETA: 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging

Check the merge workflow status
here

pytorch-bot bot added the release notes: AO frontend label Dec 27, 2022

github-actions bot added the release notes: quantization release notes category label Dec 27, 2022

andrewor14 approved these changes Dec 30, 2022

View reviewed changes

pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Jan 3, 2023

pytorchmergebot added the Merged label Jan 4, 2023

pytorchmergebot closed this in ebb7f20 Jan 4, 2023

facebook-github-bot deleted the gh/vkuzo/524/head branch June 8, 2023 18:58

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

quant: make various configs printable #91419

quant: make various configs printable #91419

vkuzo commented Dec 27, 2022 •

edited

linux-foundation-easycla bot commented Dec 27, 2022 •

edited

pytorch-bot bot commented Dec 27, 2022 •

edited

andrewor14 left a comment

vkuzo commented Jan 3, 2023

pytorch-bot bot commented Jan 3, 2023

vkuzo commented Jan 3, 2023

pytorch-bot bot commented Jan 3, 2023

vkuzo commented Jan 3, 2023

pytorchmergebot commented Jan 3, 2023

pytorchmergebot commented Jan 3, 2023

vkuzo commented Jan 3, 2023

pytorchmergebot commented Jan 3, 2023

clee2000 commented Jan 4, 2023

vkuzo commented Jan 4, 2023

pytorchmergebot commented Jan 4, 2023

pytorchmergebot commented Jan 4, 2023

vkuzo commented Jan 4, 2023

pytorchmergebot commented Jan 4, 2023

quant: make various configs printable #91419

quant: make various configs printable #91419

Conversation

vkuzo commented Dec 27, 2022 • edited

linux-foundation-easycla bot commented Dec 27, 2022 • edited

pytorch-bot bot commented Dec 27, 2022 • edited

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/91419

✅ No Failures

andrewor14 left a comment

Choose a reason for hiding this comment

vkuzo commented Jan 3, 2023

pytorch-bot bot commented Jan 3, 2023

vkuzo commented Jan 3, 2023

pytorch-bot bot commented Jan 3, 2023

PyTorchBot Help

Merge

Revert

Rebase

Label

Dr CI

vkuzo commented Jan 3, 2023

pytorchmergebot commented Jan 3, 2023

pytorchmergebot commented Jan 3, 2023

vkuzo commented Jan 3, 2023

pytorchmergebot commented Jan 3, 2023

Merge failed

clee2000 commented Jan 4, 2023

vkuzo commented Jan 4, 2023

pytorchmergebot commented Jan 4, 2023

pytorchmergebot commented Jan 4, 2023

vkuzo commented Jan 4, 2023

pytorchmergebot commented Jan 4, 2023

Merge started

vkuzo commented Dec 27, 2022 •

edited

linux-foundation-easycla bot commented Dec 27, 2022 •

edited

pytorch-bot bot commented Dec 27, 2022 •

edited