[Quant] [PT2] Add ConvBNAdd(ReLU) Annotation into X86InductorQuantizer #111281
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/111281
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 6a9bf6e with merge base a126bbf ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
leslie-fang-intel
changed the title
…torQuantizer" **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
jgong5
approved these changes
Oct 23, 2023
…torQuantizer" **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
|
Hi @jerryzh168 @andrewor14, Please also kindly help to take a look of this PR. |
jerryzh168
reviewed
Oct 31, 2023
jerryzh168
reviewed
Oct 31, 2023
| if n.target == torch.ops.aten.relu.default: | ||
| assert relu_node is None | ||
| relu_node = n | ||
| if (n.target in [torch.ops.aten.add_.Tensor, torch.ops.aten.add.Tensor]) and ( |
There was a problem hiding this comment.
OK we really should move these to quantizer..
jerryzh168
approved these changes
Oct 31, 2023
…torQuantizer" **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
…torQuantizer" **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
…torQuantizer" **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
…torQuantizer" **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng Xia-Weiwen wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Nov 1, 2023
ghstack-source-id: 2df2291 Pull Request resolved: pytorch#111281
|
@pytorchbot merge |
Merge startedYour 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 |
andrewor14
reviewed
Nov 2, 2023
| [True, False], # has_bias | ||
| [True, False], # relu_is_inplace | ||
| [True, False], # has_add | ||
| [True, False], # add_is_inplace |
There was a problem hiding this comment.
Just saw this. Just wanted to point out that this exponentially increases the number of patterns we need to match against. Right now we have 6 options here + 1 for cuda vs not cuda. That's already 128 patterns. I'm adding quantized bias support here (#112528) which adds another dimension, bringing this up to 256 patterns. This seems concerning to me.
There was a problem hiding this comment.
Probably fine for these two PRs but I think we should really think about how to push some of this functionality into the subgraph rewriter so we don't have hundreds of patterns to match. cc @jerryzh168
xuhancn
pushed a commit
to xuhancn/pytorch
that referenced
this pull request
Nov 7, 2023
pytorch#111281) **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` Pull Request resolved: pytorch#111281 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: pytorch#111280
Skylion007
pushed a commit
to Skylion007/pytorch
that referenced
this pull request
Nov 14, 2023
pytorch#111281) **Summary** This PR adds ConvBNAdd(ReLU) QAT Annotation into `X86InductorQuantizer`. **Test Plan** ``` python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_with_quantizer_api python -m pytest test_x86inductor_quantizer.py -k test_qat_conv2d_binary_unary_with_quantizer_api python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_add_relu ``` Pull Request resolved: pytorch#111281 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: pytorch#111280
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Summary
This PR adds ConvBNAdd(ReLU) QAT Annotation into
X86InductorQuantizer.Test Plan
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @Xia-Weiwen @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler