[pt2e][quant] Ensure BN node is erased after convert #131651

andrewor14 · 2024-07-24T14:25:01Z

Stack from ghstack (oldest at bottom):

-> [pt2e][quant] Ensure BN node is erased after convert #131651

Summary: Previously, when folding BN into conv, we rely on DCE
to clean up the unused BN node from the graph. This works if
the model is already in eval mode, but fails if the model is
still in train mode because DCE doesn't remove nodes with
potential side effects (in this case _native_batch_norm_legit).
This required users to move the model to eval mode before calling
convert in order to get a properly DCE'd graph.

To solve this, we manually erase the BN node after folding
instead of relying on DCE. This relaxes the ordering constraints
between move_exported_model_to_eval and convert_pt2e.

Test Plan:
python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node
python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node

Reviewers: jerryzh168, yushangdi

Subscribers: jerryzh168, yushangdi, supriyar

Differential Revision: D60520149

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar [ghstack-poisoned]

pytorch-bot · 2024-07-24T14:25:06Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/131651

📄 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.

✅ You can merge normally! (15 Unrelated Failures)

As of commit f76b436 with merge base a672f6c ():

FLAKY - The following job failed but was likely due to flakiness present on trunk:

trunk / linux-focal-cuda12.4-py3.10-gcc9-sm86 / test (default, 5, 5, amz2023.linux.g5.4xlarge.nvidia.gpu) (gh) (similar failure)
'test/inductor/test_cudacodecache.py::TestCUDACodeCache::test_async_compile'

BROKEN TRUNK - The following jobs failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

pull / linux-focal-cuda12.1-py3.10-gcc9 / test (default, 3, 5, amz2023.linux.4xlarge.nvidia.gpu) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-cuda12.1-py3.10-gcc9-sm86 / test (default, 2, 5, amz2023.linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-py3.11-clang10 / test (crossref, 1, 2, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-py3.11-clang10 / test (default, 2, 4, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-py3.12-clang10 / test (default, 2, 4, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-py3.12-clang10-experimental-split-build / test (default, 2, 3, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-py3.8-clang10 / test (crossref, 1, 2, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-focal-py3.8-clang10 / test (default, 2, 4, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-jammy-py3.10-clang15-asan / test (default, 3, 6, amz2023.linux.4xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
pull / linux-jammy-py3.8-gcc11 / test (default, 2, 4, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
trunk / linux-focal-cuda12.4-py3.10-gcc9-experimental-split-build-test / test (default, 2, 5, amz2023.linux.4xlarge.nvidia.gpu) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
trunk / linux-focal-cuda12.4-py3.10-gcc9-experimental-split-build-test / test (nogpu_AVX512, 1, 1, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
trunk / linux-focal-cuda12.4-py3.10-gcc9-experimental-split-build-test / test (nogpu_NO_AVX2, 1, 1, amz2023.linux.2xlarge) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names
trunk / linux-focal-cuda12.4-py3.10-gcc9-sm86 / test (default, 2, 5, amz2023.linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
test_public_bindings.py::TestPublicBindings::test_correct_module_names

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

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar ghstack-source-id: f2e3c23 Pull Request resolved: #131651

yushangdi

LGTM

andrewor14 · 2024-07-24T17:17:16Z

@pytorchbot merge

pytorchmergebot · 2024-07-24T17:19:01Z

Merge started

Your change will be merged once all checks pass (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

pytorchmergebot · 2024-07-24T23:17:44Z

The merge job was canceled or timed out. This most often happen if two merge requests were issued for the same PR, or if merge job was waiting for more than 6 hours for tests to finish. In later case, please do not hesitate to reissue the merge command
For more information see pytorch-bot wiki.

andrewor14 · 2024-07-25T14:39:53Z

@pytorchbot merge

pytorchmergebot · 2024-07-25T14:41:44Z

Merge started

Your change will be merged once all checks pass (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

pytorchmergebot · 2024-07-25T14:41:55Z

Merge failed

Reason: Command git -C /home/runner/work/pytorch/pytorch cherry-pick -x a1eb8a05d01ad9955106d8d79b8f3448a185a200 returned non-zero exit code 1

Auto-merging torch/ao/quantization/pt2e/utils.py
CONFLICT (content): Merge conflict in torch/ao/quantization/pt2e/utils.py
error: could not apply a1eb8a05d0... [pt2e][quant] Ensure BN node is erased after convert
hint: After resolving the conflicts, mark them with
hint: "git add/rm <pathspec>", then run
hint: "git cherry-pick --continue".
hint: You can instead skip this commit with "git cherry-pick --skip".
hint: To abort and get back to the state before "git cherry-pick",
hint: run "git cherry-pick --abort".
hint: Disable this message with "git config advice.mergeConflict false"

Details for Dev Infra team

Raised by workflow job

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar [ghstack-poisoned]

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar ghstack-source-id: e2f5f5a Pull Request resolved: #131651

andrewor14 · 2024-07-26T15:23:29Z

@pytorchbot merge

pytorchmergebot · 2024-07-26T15:25:17Z

Merge started

Your change will be merged once all checks pass (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

ZainRizvi · 2024-07-29T16:40:46Z

@pytorchbot revert -m "breaking internal builds" -c ghfirst

Hi @andrewor14, the new test is failing internally for some reason. Please take a look at D60325176 for the details

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar [ghstack-poisoned]

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar ghstack-source-id: 6901545 Pull Request resolved: #131651

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar [ghstack-poisoned]

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar ghstack-source-id: 879a774 Pull Request resolved: #131651

andrewor14 · 2024-07-31T14:58:23Z

@andrewor14 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

andrewor14 · 2024-07-31T19:34:14Z

@pytorchbot merge

pytorchmergebot · 2024-07-31T19:35:54Z

Merge failed

Reason: This PR has internal changes and must be landed via Phabricator! Please try reimporting/rexporting the PR!

Details for Dev Infra team

Raised by workflow job

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar Differential Revision: [D60520149](https://our.internmc.facebook.com/intern/diff/D60520149) [ghstack-poisoned]

Summary: Previously, when folding BN into conv, we rely on DCE to clean up the unused BN node from the graph. This works if the model is already in eval mode, but fails if the model is still in train mode because DCE doesn't remove nodes with potential side effects (in this case `_native_batch_norm_legit`). This required users to move the model to eval mode before calling convert in order to get a properly DCE'd graph. To solve this, we manually erase the BN node after folding instead of relying on DCE. This relaxes the ordering constraints between `move_exported_model_to_eval` and `convert_pt2e`. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn1d.test_fold_bn_erases_bn_node python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d.test_fold_bn_erases_bn_node Reviewers: jerryzh168, yushangdi Subscribers: jerryzh168, yushangdi, supriyar ghstack-source-id: d77c2fe Pull Request resolved: #131651

andrewor14 · 2024-08-05T16:23:42Z

@andrewor14 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

Summary: - make default DCE pass check schema, - need to rebase onto pytorch/pytorch#131651 after it's in phabricator (for now the change is manually added). - mark Proxy dump as NotImplemented for better error msg - Remove Proxy from tensors when dumping models, as Proxy cannot be dumped. More details in https://docs.google.com/document/d/1G5vmTXjzxoyVGRI2kpA1gQukK_Glyg2NrE0Oh6Nlg9A/edit?usp=sharing. Reviewed By: angelayi Differential Revision: D60319175

Summary: - make default DCE pass check schema, - need to rebase onto pytorch#131651 after it's in phabricator (for now the change is manually added). - mark Proxy dump as NotImplemented for better error msg - Remove Proxy from tensors when dumping models, as Proxy cannot be dumped. More details in https://docs.google.com/document/d/1G5vmTXjzxoyVGRI2kpA1gQukK_Glyg2NrE0Oh6Nlg9A/edit?usp=sharing. Test Plan: CI ``` - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- -r qat_conv2d - test_export.py - buck2 run 'fbcode//mode/dev-nosan' fbcode//modai/test:test_modai -- -r test_qat_stinson_htp_export - buck2 run 'fbcode//mode/dev-nosan' fbcode//vizard_projects/ml_depth/tests:test_model -- -r test_qat_model_et - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test:fx -- -r dce - buck2 run 'fbcode//mode/dev-nosan' fbcode//bolt/nn/executorch/backends/tests:qnn_test -- -r test_qat_bias=False,use_3d_input=False - buck2 run 'fbcode//mode/dev-nosan' fbcode//bolt/nn/executorch/backends/tests:qnn_test -- -r test_qat_bias=True,use_3d_input=False - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- -r test_fold_bn_erases_bn_node ``` Reviewed By: angelayi Differential Revision: D60319175

Summary: X-link: pytorch/pytorch#132764 Pull Request resolved: pytorch#4565 - make default DCE pass check schema, - need to rebase onto pytorch/pytorch#131651 after it's in phabricator (for now the change is manually added). - mark Proxy dump as NotImplemented for better error msg - Remove Proxy from tensors when dumping models, as Proxy cannot be dumped. More details in https://docs.google.com/document/d/1G5vmTXjzxoyVGRI2kpA1gQukK_Glyg2NrE0Oh6Nlg9A/edit?usp=sharing. Reviewed By: angelayi Differential Revision: D60319175

facebook-github-bot · 2024-08-06T16:35:14Z

@pytorchbot merge -f 'Landed internally'

(Initiating merge automatically since Phabricator Diff has merged, using force because this PR might not pass merge_rules.json but landed internally)

Summary: Pull Request resolved: pytorch#132764 X-link: pytorch/executorch#4565 - make default DCE pass check schema, - need to rebase onto pytorch#131651 after it's in phabricator (for now the change is manually added). - mark Proxy dump as NotImplemented for better error msg - Remove Proxy from tensors when dumping models, as Proxy cannot be dumped. More details in https://docs.google.com/document/d/1G5vmTXjzxoyVGRI2kpA1gQukK_Glyg2NrE0Oh6Nlg9A/edit?usp=sharing. Test Plan: CI ``` - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- -r qat_conv2d - test_export.py - buck2 run 'fbcode//mode/dev-nosan' fbcode//modai/test:test_modai -- -r test_qat_stinson_htp_export - buck2 run 'fbcode//mode/dev-nosan' fbcode//vizard_projects/ml_depth/tests:test_model -- -r test_qat_model_et - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test:fx -- -r dce - buck2 run 'fbcode//mode/dev-nosan' fbcode//bolt/nn/executorch/backends/tests:qnn_test -- -r test_qat_bias=False,use_3d_input=False - buck2 run 'fbcode//mode/dev-nosan' fbcode//bolt/nn/executorch/backends/tests:qnn_test -- -r test_qat_bias=True,use_3d_input=False - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- -r test_fold_bn_erases_bn_node ``` Reviewed By: angelayi Differential Revision: D60319175

pytorchmergebot · 2024-08-06T16:37:27Z

Merge started

Your change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use -f as last resort and instead consider -i/--ignore-current to continue the merge ignoring current failures. This will allow currently pending tests to finish and report signal before the merge.

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

Summary: X-link: pytorch/pytorch#132764 Pull Request resolved: pytorch#4565 - make default DCE pass check schema, - need to rebase onto pytorch/pytorch#131651 after it's in phabricator (for now the change is manually added). - mark Proxy dump as NotImplemented for better error msg - Remove Proxy from tensors when dumping models, as Proxy cannot be dumped. More details in https://docs.google.com/document/d/1G5vmTXjzxoyVGRI2kpA1gQukK_Glyg2NrE0Oh6Nlg9A/edit?usp=sharing. Reviewed By: angelayi Differential Revision: D60319175

Summary: - make default DCE pass check schema, - need to rebase onto #131651 after it's in phabricator (for now the change is manually added). - mark Proxy dump as NotImplemented for better error msg - Remove Proxy from tensors when dumping models, as Proxy cannot be dumped. More details in https://docs.google.com/document/d/1G5vmTXjzxoyVGRI2kpA1gQukK_Glyg2NrE0Oh6Nlg9A/edit?usp=sharing. Test Plan: CI ``` - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- -r qat_conv2d - test_export.py - buck2 run 'fbcode//mode/dev-nosan' fbcode//modai/test:test_modai -- -r test_qat_stinson_htp_export - buck2 run 'fbcode//mode/dev-nosan' fbcode//vizard_projects/ml_depth/tests:test_model -- -r test_qat_model_et - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test:fx -- -r dce - buck2 run 'fbcode//mode/dev-nosan' fbcode//bolt/nn/executorch/backends/tests:qnn_test -- -r test_qat_bias=False,use_3d_input=False - buck2 run 'fbcode//mode/dev-nosan' fbcode//bolt/nn/executorch/backends/tests:qnn_test -- -r test_qat_bias=True,use_3d_input=False - buck2 run 'fbcode//mode/dev-nosan' fbcode//caffe2/test/quantization:test_quantization -- -r test_fold_bn_erases_bn_node ``` Reviewed By: angelayi Differential Revision: D60319175 Pull Request resolved: #132764 Approved by: https://github.com/angelayi

andrewor14 requested a review from jerryzh168 as a code owner July 24, 2024 14:25

pytorch-bot bot added the release notes: quantization release notes category label Jul 24, 2024

andrewor14 requested review from yushangdi and leslie-fang-intel July 24, 2024 14:25

yushangdi approved these changes Jul 24, 2024

View reviewed changes

pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Jul 24, 2024

pytorchmergebot added the merging label Jul 24, 2024

leslie-fang-intel mentioned this pull request Jul 25, 2024

[inductor][cpu] QAT performance regression in 2024-07-20 nightly release #131664

Closed

pytorchmergebot removed the merging label Jul 25, 2024

pytorchmergebot added the merging label Jul 26, 2024

pytorchmergebot closed this in eba2ffd Jul 26, 2024

pytorchmergebot added Merged and removed merging labels Jul 26, 2024

pytorchmergebot reopened this Jul 29, 2024

henrylhtsang mentioned this pull request Jul 31, 2024

[BE][typing] fix types in common pruning #132309

Closed

pytorchmergebot added the merging label Jul 31, 2024

pytorchmergebot removed the merging label Jul 31, 2024

leslie-fang-intel approved these changes Aug 1, 2024

View reviewed changes

yushangdi mentioned this pull request Aug 6, 2024

More robust DCE pass pytorch/executorch#4565

Closed

yushangdi mentioned this pull request Aug 6, 2024

[export][fx] More robust DCE pass #132764

Closed

pytorchmergebot added the merging label Aug 6, 2024

pytorchmergebot closed this in fc7849b Aug 6, 2024

pytorchmergebot removed the merging label Aug 6, 2024

github-actions bot deleted the gh/andrewor14/52/head branch September 6, 2024 02:03

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[pt2e][quant] Ensure BN node is erased after convert #131651

[pt2e][quant] Ensure BN node is erased after convert #131651

andrewor14 commented Jul 24, 2024 •

edited

Loading

pytorch-bot bot commented Jul 24, 2024 •

edited

Loading

yushangdi left a comment

andrewor14 commented Jul 24, 2024

pytorchmergebot commented Jul 24, 2024

pytorchmergebot commented Jul 24, 2024

andrewor14 commented Jul 25, 2024

pytorchmergebot commented Jul 25, 2024

pytorchmergebot commented Jul 25, 2024

andrewor14 commented Jul 26, 2024

pytorchmergebot commented Jul 26, 2024

ZainRizvi commented Jul 29, 2024

andrewor14 commented Jul 31, 2024

andrewor14 commented Jul 31, 2024

pytorchmergebot commented Jul 31, 2024

andrewor14 commented Aug 5, 2024

facebook-github-bot commented Aug 6, 2024

pytorchmergebot commented Aug 6, 2024

[pt2e][quant] Ensure BN node is erased after convert #131651

[pt2e][quant] Ensure BN node is erased after convert #131651

Conversation

andrewor14 commented Jul 24, 2024 • edited Loading

pytorch-bot bot commented Jul 24, 2024 • edited Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/131651

✅ You can merge normally! (15 Unrelated Failures)

yushangdi left a comment

Choose a reason for hiding this comment

andrewor14 commented Jul 24, 2024

pytorchmergebot commented Jul 24, 2024

Merge started

pytorchmergebot commented Jul 24, 2024

andrewor14 commented Jul 25, 2024

pytorchmergebot commented Jul 25, 2024

Merge started

pytorchmergebot commented Jul 25, 2024

Merge failed

andrewor14 commented Jul 26, 2024

pytorchmergebot commented Jul 26, 2024

Merge started

ZainRizvi commented Jul 29, 2024

andrewor14 commented Jul 31, 2024

andrewor14 commented Jul 31, 2024

pytorchmergebot commented Jul 31, 2024

Merge failed

andrewor14 commented Aug 5, 2024

facebook-github-bot commented Aug 6, 2024

pytorchmergebot commented Aug 6, 2024

Merge started

andrewor14 commented Jul 24, 2024 •

edited

Loading

pytorch-bot bot commented Jul 24, 2024 •

edited

Loading