[ONNX] Add quantization support to more single output ops

[justinchuby]

trafficstars

Stack from ghstack (oldest at bottom):

• -> #83008
• #83007
• #83006

#80039

• Remove magic number and assign it to INT64_MAX

[facebook-github-bot]

:link: Helpful links

• :test_tube:  See artifacts and rendered test results at hud.pytorch.org/pr/83008
• :x: Python docsfailed to build
• :page_facing_up:  Preview C++ docs built from this PR
• :question:Need help or want to give feedback on the CI? Visit our office hours

:x: 1 New Failures

As of commit cd6feb0875 (more details on the Dr. CI page):

Expand to see more

---

• 1/1 failures introduced in this PR

---

:detective: 1 new failure recognized by patterns

The following CI failures do not appear to be due to upstream breakages

pull / linux-docs / build-docs (python) (1/1)

Step: "Unknown" (full log | diagnosis details)

2022-08-23T05:18:17.6475546Z ##[error]The operation was canceled.

2022-08-22T23:24:21.5829999Z copying images... [ 97%] _static/img/tensorboard/add_images.png
2022-08-22T23:24:21.5831868Z copying images... [100%] _static/img/tensorboard/add_hparam.png
2022-08-22T23:24:21.5833426Z 
2022-08-22T23:24:21.6057519Z copying static files... done
2022-08-22T23:24:21.6058126Z copying extra files... done
2022-08-22T23:24:22.0276905Z dumping search index in English (code: en)... done
2022-08-22T23:24:22.1307989Z dumping object inventory... done
2022-08-22T23:24:22.1311164Z build succeeded.
2022-08-22T23:24:22.1312815Z 
2022-08-22T23:24:22.1313248Z The HTML pages are in build/html.
2022-08-23T05:18:17.6475546Z ##[error]The operation was canceled.
2022-08-23T05:18:17.6496048Z Prepare all required actions
2022-08-23T05:18:17.6513162Z ##[group]Run ./.github/actions/chown-workspace
2022-08-23T05:18:17.6513372Z ##[endgroup]
2022-08-23T05:18:17.6526768Z ##[group]Run docker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .
2022-08-23T05:18:17.6527113Z [36;1mdocker run --rm -v "$(pwd)":/v -w /v "${ALPINE_IMAGE}" chown -R "$(id -u):$(id -g)" .[0m
2022-08-23T05:18:17.6537604Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2022-08-23T05:18:17.6537818Z env:
2022-08-23T05:18:17.6538053Z   ALPINE_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine
2022-08-23T05:18:17.6538281Z ##[endgroup]
2022-08-23T05:18:19.1124258Z Post job cleanup.

---

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.

[justinchuby]

Commit message:

Single output ops (1/2)

• Implement quantization support for
  • quantized::sigmoid
  • quantized::instance_norm
  • aten::reshape
  • aten::reshape_as
  • aten::sum
  • aten::mean
  • aten::prod
  • aten::t
  • aten::numpy_T
  • aten::expand
  • aten::expand_as
  • aten::embedding
  • aten::embedding_bag
  • aten::view
  • aten::select
  • aten::eq
  • aten::ne
  • aten::gt
  • aten::lt
  • aten::le
  • aten::ge
  • aten::native_layer_norm
  • aten::layer_norm
  • aten::elu
  • aten::selu
  • aten::maximum
  • aten::minimum
  • aten::amax
  • aten::amin
  • aten::hardtanh
  • aten::hardswish
  • aten::group_norm
  • aten::as_strided
• Avoid modifying functions in quantized_args and have the wrapper closed over scale and zero_point instead
• Remove magic number and assign it to INT64_MAX
• implement _unpack_quantized_tensor for handling quantized tensor unpacking to separate the logic from tuple unpacking and for clearer error handling

[justinchuby]

@BowenBao ptal

[BowenBao]

Please checkout CI failure

[justinchuby]

@BowenBao please take another look

[justinchuby]

@pytorchbot merge -g

[pytorchmergebot]

@pytorchbot successfully started a merge job. Check the current status here. The merge job was triggered with the green (-g) flag. This means that your change will be merged once all checks on your PR have passed (ETA: 0-4 Hours). If this is not the intended behavior, feel free to use some of the other merge options in the wiki. Please reach out to the PyTorch DevX Team with feedback or questions!

[justinchuby]

@pytorchbot merge -f "All checks passed"

[pytorchmergebot]

The merge job was canceled. If you believe this is a mistake,then you can re trigger it through pytorch-bot.

[pytorchmergebot]

@pytorchbot successfully started a merge job. Check the current status here. The merge job was triggered with the force (-f) flag. This means your change will be merged immediately, bypassing any CI checks (ETA: 1-5 minutes). If this is not the intended behavior, feel free to use some of the other merge options in the wiki. Please reach out to the PyTorch DevX Team with feedback or questions!