[ONNX] First version of quantized model export: Support quantized.Linear #69232

jiafatom · 2021-12-01T17:19:09Z

No description provided.

pytorch-probot · 2021-12-01T17:19:12Z

CI Flow Status

⚛️ CI Flow

Ruleset - Version: v1
Ruleset - File: https://github.com/jiafatom/pytorch/blob/85a975800100b26dc75088edf0885ea1de8c2b10/.github/generated-ciflow-ruleset.json
PR ciflow labels: ciflow/default

Workflows	Labels (bold enabled)	Status
Triggered Workflows
linux-bionic-py3.6-clang9	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/noarch`, `ciflow/xla`	✅ triggered
linux-vulkan-bionic-py3.6-clang9	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/vulkan`	✅ triggered
linux-xenial-cuda11.3-py3.6-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/default`, `ciflow/linux`	✅ triggered
linux-xenial-py3-clang5-mobile-build	`ciflow/all`, `ciflow/default`, `ciflow/linux`, `ciflow/mobile`	✅ triggered
linux-xenial-py3-clang5-mobile-custom-build-dynamic	`ciflow/all`, `ciflow/default`, `ciflow/linux`, `ciflow/mobile`	✅ triggered
linux-xenial-py3-clang5-mobile-custom-build-static	`ciflow/all`, `ciflow/default`, `ciflow/linux`, `ciflow/mobile`	✅ triggered
linux-xenial-py3.6-clang7-asan	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/sanitizers`	✅ triggered
linux-xenial-py3.6-clang7-onnx	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/onnx`	✅ triggered
linux-xenial-py3.6-gcc5.4	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`	✅ triggered
linux-xenial-py3.6-gcc7	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`	✅ triggered
linux-xenial-py3.6-gcc7-bazel-test	`ciflow/all`, `ciflow/bazel`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`	✅ triggered
pytorch-linux-xenial-py3-clang5-android-ndk-r19c-gradle-custom-build-single	`ciflow/all`, `ciflow/android`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`	✅ triggered
pytorch-linux-xenial-py3-clang5-android-ndk-r19c-gradle-custom-build-single-full-jit	`ciflow/all`, `ciflow/android`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`	✅ triggered
win-vs2019-cpu-py3	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/win`	✅ triggered
win-vs2019-cuda11.3-py3	`ciflow/all`, `ciflow/cuda`, `ciflow/default`, `ciflow/win`	✅ triggered
Skipped Workflows
caffe2-linux-xenial-py3.6-gcc5.4	`ciflow/all`, `ciflow/cpu`, `ciflow/linux`	🚫 skipped
docker-builds	`ciflow/all`	🚫 skipped
ios-12-5-1-arm64	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-arm64-coreml	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-arm64-custom-ops	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-arm64-full-jit	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-arm64-metal	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-x86-64	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-x86-64-coreml	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
ios-12-5-1-x86-64-full-jit	`ciflow/all`, `ciflow/ios`, `ciflow/macos`	🚫 skipped
libtorch-linux-xenial-cuda10.2-py3.6-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/libtorch`, `ciflow/linux`	🚫 skipped
libtorch-linux-xenial-cuda11.3-py3.6-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/libtorch`, `ciflow/linux`	🚫 skipped
linux-bionic-cuda10.2-py3.9-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/slow`	🚫 skipped
linux-xenial-py3-clang5-mobile-code-analysis	`ciflow/all`, `ciflow/linux`, `ciflow/mobile`	🚫 skipped
parallelnative-linux-xenial-py3.6-gcc5.4	`ciflow/all`, `ciflow/cpu`, `ciflow/linux`	🚫 skipped
periodic-libtorch-linux-xenial-cuda11.1-py3.6-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/libtorch`, `ciflow/linux`, `ciflow/scheduled`	🚫 skipped
periodic-linux-xenial-cuda10.2-py3-gcc7-slow-gradcheck	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/scheduled`, `ciflow/slow`, `ciflow/slow-gradcheck`	🚫 skipped
periodic-linux-xenial-cuda11.1-py3.6-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/scheduled`	🚫 skipped
periodic-win-vs2019-cuda11.1-py3	`ciflow/all`, `ciflow/cuda`, `ciflow/scheduled`, `ciflow/win`	🚫 skipped

You can add a comment to the PR and tag @pytorchbot with the following commands:

# ciflow rerun, "ciflow/default" will always be added automatically
@pytorchbot ciflow rerun

# ciflow rerun with additional labels "-l <ciflow/label_name>", which is equivalent to adding these labels manually and trigger the rerun
@pytorchbot ciflow rerun -l ciflow/scheduled -l ciflow/slow

For more information, please take a look at the CI Flow Wiki.

facebook-github-bot · 2021-12-01T17:19:15Z

🔗 Helpful links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/69232
🔧 Opt-in to CIFlow to control what jobs run on your PRs

💊 CI failures summary and remediations

As of commit 85a9758 (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.

garymm

Thanks for this change!
I didn't finish reviewing all of it. I'll try to finish tomorrow.

torch/onnx/utils.py

test/onnx/test_pytorch_onnx_onnxruntime.py

torch/csrc/jit/passes/onnx/peephole.cpp

garymm

Finished reading through the code once.

test/onnx/test_pytorch_onnx_onnxruntime.py

torch/csrc/jit/passes/onnx/unpack_quantized_weights.cpp

torch/onnx/utils.py

test/onnx/test_pytorch_onnx_onnxruntime.py

torch/csrc/jit/passes/onnx/peephole.cpp

torch/csrc/jit/passes/onnx/unpack_quantized_weights.cpp

torch/onnx/symbolic_opset10.py

torch/onnx/utils.py

garymm

Thanks!

torch/csrc/jit/passes/onnx/peephole.cpp

torch/onnx/symbolic_opset10.py

torch/csrc/jit/passes/onnx/unpack_quantized_weights.cpp

jiafatom · 2021-12-10T00:44:33Z

The failed tests look unrelated, merging this PR.

…ear (pytorch#69232) Co-authored-by: David Fan <jiafa@microsoft.com>

…ear (#69232) Co-authored-by: David Fan <jiafa@microsoft.com> [ghstack-poisoned]

…antized.Linear (#69232)" Co-authored-by: David Fan <jiafamicrosoft.com> [ghstack-poisoned]

…ear (#69232) Co-authored-by: David Fan <jiafamicrosoft.com> Pull Request resolved: #72986

…ear (#69232) (#72986) Summary: Pull Request resolved: #72986 Test Plan: automation Reviewed By: malfet, seemethere Differential Revision: D34347597 fbshipit-source-id: 2772dc1e5deef81ed02dcb8c63112c6b60e7b283 Co-authored-by: David Fan <jiafamicrosoft.com>

jiafatom requested review from BowenBao and shubhambhokare1 as code owners December 1, 2021 17:19

pytorch-probot bot added the ciflow/default label Dec 1, 2021

facebook-github-bot added the cla signed label Dec 1, 2021

facebook-github-bot added the oncall: jit Add this issue/PR to JIT oncall triage queue label Dec 1, 2021

pytorchbot added the open source label Dec 1, 2021

jiafatom force-pushed the quant_model branch 10 times, most recently from 1bba4d7 to cf65772 Compare December 2, 2021 01:28

garymm self-assigned this Dec 7, 2021

garymm requested changes Dec 8, 2021

View reviewed changes

jiafatom force-pushed the quant_model branch 4 times, most recently from 8dd5ec9 to 822a8db Compare December 8, 2021 23:56

jiafatom requested a review from garymm December 9, 2021 00:24

jiafatom force-pushed the quant_model branch from 822a8db to 3fe2082 Compare December 9, 2021 01:47

garymm requested changes Dec 9, 2021

View reviewed changes

jiafatom force-pushed the quant_model branch 2 times, most recently from 96d56f4 to 0708424 Compare December 9, 2021 21:32

jiafatom requested a review from garymm December 9, 2021 21:34

jiafatom force-pushed the quant_model branch from 0708424 to cf85d0d Compare December 9, 2021 22:05

garymm approved these changes Dec 9, 2021

View reviewed changes

torch/csrc/jit/passes/onnx/peephole.cpp Show resolved Hide resolved

torch/onnx/symbolic_opset10.py Show resolved Hide resolved

torch/csrc/jit/passes/onnx/unpack_quantized_weights.cpp Show resolved Hide resolved

torch/csrc/jit/passes/onnx/unpack_quantized_weights.cpp Show resolved Hide resolved

Quantized model

85a9758

jiafatom force-pushed the quant_model branch from cf85d0d to 85a9758 Compare December 9, 2021 23:00

jiafatom merged commit 7efac59 into pytorch:onnx_ms_1 Dec 10, 2021

jiafatom deleted the quant_model branch December 10, 2021 00:46

BowenBao mentioned this pull request Jan 4, 2022

Testing ONNX branch CI #70586

Closed

BowenBao pushed a commit to BowenBao/pytorch that referenced this pull request Jan 5, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

b79d6ba

…ear (pytorch#69232) Co-authored-by: David Fan <jiafa@microsoft.com>

BowenBao pushed a commit to BowenBao/pytorch that referenced this pull request Jan 21, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

23a131a

…ear (pytorch#69232) Co-authored-by: David Fan <jiafa@microsoft.com>

BowenBao pushed a commit to BowenBao/pytorch that referenced this pull request Jan 21, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

8d594b6

…ear (pytorch#69232) Co-authored-by: David Fan <jiafa@microsoft.com>

BowenBao pushed a commit to BowenBao/pytorch that referenced this pull request Jan 31, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

792ec61

…ear (pytorch#69232) Co-authored-by: David Fan <jiafa@microsoft.com>

BowenBao added a commit that referenced this pull request Feb 17, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

0b4be6d

…ear (#69232) Co-authored-by: David Fan <jiafa@microsoft.com> [ghstack-poisoned]

BowenBao added a commit that referenced this pull request Feb 17, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

1afb34b

…ear (#69232) Co-authored-by: David Fan <jiafa@microsoft.com> [ghstack-poisoned]

BowenBao added a commit that referenced this pull request Feb 17, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

dc83af1

…ear (#69232) Co-authored-by: David Fan <jiafa@microsoft.com> [ghstack-poisoned]

BowenBao added a commit that referenced this pull request Feb 17, 2022

Update on "[ONNX] First version of quantized model export: Support qu…

3782ffb

…antized.Linear (#69232)" Co-authored-by: David Fan <jiafamicrosoft.com> [ghstack-poisoned]

pytorchmergebot pushed a commit that referenced this pull request Feb 18, 2022

[ONNX] First version of quantized model export: Support quantized.Lin…

32f6a1e

…ear (#69232) Co-authored-by: David Fan <jiafamicrosoft.com> Pull Request resolved: #72986

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[ONNX] First version of quantized model export: Support quantized.Linear #69232

[ONNX] First version of quantized model export: Support quantized.Linear #69232

jiafatom commented Dec 1, 2021

pytorch-probot bot commented Dec 1, 2021 •

edited

Loading

⚛️ CI Flow

facebook-github-bot commented Dec 1, 2021 •

edited

Loading

garymm left a comment

garymm left a comment

garymm left a comment

jiafatom commented Dec 10, 2021

[ONNX] First version of quantized model export: Support quantized.Linear #69232

[ONNX] First version of quantized model export: Support quantized.Linear #69232

Conversation

jiafatom commented Dec 1, 2021

pytorch-probot bot commented Dec 1, 2021 • edited Loading

⚛️ CI Flow

facebook-github-bot commented Dec 1, 2021 • edited Loading

🔗 Helpful links

💊 CI failures summary and remediations

garymm left a comment

Choose a reason for hiding this comment

garymm left a comment

Choose a reason for hiding this comment

garymm left a comment

Choose a reason for hiding this comment

jiafatom commented Dec 10, 2021

pytorch-probot bot commented Dec 1, 2021 •

edited

Loading

facebook-github-bot commented Dec 1, 2021 •

edited

Loading