[quant][fx] Move the remaining fixed qparam ops to backend_config_dict

[jerryzh168]

Stack from ghstack (oldest at bottom):

• [quant][fx] Using native backend_config_dict in fusion #75378
• [quant][fx] Remove "additional_fusion_pattern" from prepare_custom_config_dict #75377
• [quant][fx] Move all fusion registrations to backend_config_dict #75318
• [quant][fx] Move embedding ops to backend_config_dict #75317
• [quant][fx] Move rnn ops to backend_config_dict #75316
• [quant][fx] Move output share qparam with input ops to backend_config_dict #75315
• -> [quant][fx] Move the remaining fixed qparam ops to backend_config_dict #75314
• [quant][fx] Add BatchNorm ops to backend_config_dict #75260
• [quant][fx] Add cat to backend_config_dict #75259
• [quant][fx] Remove the remaining registrations in BinaryOpQuantizeHandler #75258
• [quant][fx] Move all binary op configs to backend_config_dict #75241

Summary:
this is a refactor to use backend_config_dict for operators with fixed quantization parameters
api is not final yet, we'll update the api after we moved everything to backend_config_dict

Test Plan:
python test/test_quantization.py TestQuantizeFx
python test/test_quantization.py TestQuantizeFxOps
python test/test_quantization.py TestFXNumericSuiteCoreAPIs

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: D35423790

[facebook-github-bot]

🔗 Helpful links

• 🧪  See artifacts and rendered test results at hud.pytorch.org/pr/75314
• 📄  Preview Python docs built from this PR
• 📄  Preview C++ docs built from this PR
• ↩️  [fb-only] Re-run with SSH instructions
• ❓Need help or want to give feedback on the CI? Visit our office hours

💊 CI failures summary and remediations

As of commit 0eaef19 (more details on the Dr. CI page):

---

• 1/1 failures introduced in this PR

---

🕵️ 1 new failure recognized by patterns

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

pull / win-vs2019-cuda11.3-py3 / test (default, 1, 2, windows.8xlarge.nvidia.gpu) (1/1)

Step: "Setup Windows" (full log | diagnosis details | 🔁 rerun)

2022-04-07T02:53:40.0436472Z C:\actions-runner\...dfa867c7280.sh: line 2: python3: command not found

2022-04-07T02:53:39.9791738Z   BRANCH: 
2022-04-07T02:53:39.9792261Z   JOB_BASE_NAME: win-vs2019-cuda11.3-py3-test
2022-04-07T02:53:39.9792877Z   BUILD_ENVIRONMENT: win-vs2019-cuda11.3-py3
2022-04-07T02:53:39.9793382Z   PR_NUMBER: 75314
2022-04-07T02:53:39.9793881Z   SHA1: 0eaef1926c77b9111df33bde1a214837360bbb12
2022-04-07T02:53:39.9794362Z   TAG: 
2022-04-07T02:53:39.9794735Z   WORKFLOW_ID: 2105471346
2022-04-07T02:53:39.9795592Z   GITHUB_TOKEN: ***
2022-04-07T02:53:39.9796018Z ##[endgroup]
2022-04-07T02:53:40.0339725Z + python3 -m pip install -r requirements.txt
2022-04-07T02:53:40.0436472Z C:\actions-runner\_work\_temp\4944e4ba-41ec-4cb0-9180-cdfa867c7280.sh: line 2: python3: command not found
2022-04-07T02:53:40.0465363Z ##[error]Process completed with exit code 127.
2022-04-07T02:53:40.0580068Z Prepare all required actions
2022-04-07T02:53:40.0617199Z ##[group]Run ./.github/actions/teardown-win
2022-04-07T02:53:40.0617452Z with:
2022-04-07T02:53:40.0617620Z env:
2022-04-07T02:53:40.0617822Z   IN_CI: 1
2022-04-07T02:53:40.0618018Z   IS_GHA: 1
2022-04-07T02:53:40.0618220Z   GIT_DEFAULT_BRANCH: master
2022-04-07T02:53:40.0618446Z ##[endgroup]
2022-04-07T02:53:40.0723800Z ##[group]Run .github\scripts\wait_for_ssh_to_drain.ps1

---

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.

[jerryzh168]

@jerryzh168 has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.