New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Quant] [Inductor] Enable the Inductor Lowering of QConv2d post op hardtanh #114580
[Quant] [Inductor] Enable the Inductor Lowering of QConv2d post op hardtanh #114580
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/114580
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 656a829 with merge base 11f11e9 (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
ghstack-source-id: ccb9faa970d6b7b2eb00ceff7b88c583f56bbb74 Pull Request resolved: #114580
… post op hardtanh" **Summary** Enable the fusion pattern of `QConv2d -> hardtanh` lowering to `hardtanh` as `QConv2d` post operator. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_relu6_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_hardtanh_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_relu6 python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_hardtanh ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
ghstack-source-id: e5623040cf0423133d35d0dae21beae307444195 Pull Request resolved: #114580
… post op hardtanh" **Summary** Enable the fusion pattern of `QConv2d -> hardtanh` lowering to `hardtanh` as `QConv2d` post operator. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_relu6_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_hardtanh_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_relu6 python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_hardtanh ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
ghstack-source-id: ecc8e9434ffd69a36440b0cb9d5a4f72f766adc5 Pull Request resolved: #114580
… post op hardtanh" **Summary** Enable the fusion pattern of `QConv2d -> hardtanh` lowering to `hardtanh` as `QConv2d` post operator. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_relu6_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_hardtanh_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_relu6 python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_hardtanh ``` cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
ghstack-source-id: bf41d5c1a7198395f3104017632fbc850606ffb3 Pull Request resolved: pytorch#114580
@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 |
…rdtanh (pytorch#114580) **Summary** Enable the fusion pattern of `QConv2d -> hardtanh` lowering to `hardtanh` as `QConv2d` post operator. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_relu6_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qconv2d_hardtanh_cpu python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_relu6 python -m pytest test_mkldnn_pattern_matcher.py -k test_qat_qconv2d_hardtanh ``` Pull Request resolved: pytorch#114580 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: pytorch#114578, pytorch#114579
@pytorchbot merge |
Can't merge closed PR #114580 |
Stack from ghstack (oldest at bottom):
Summary
Enable the fusion pattern of
QConv2d -> hardtanh
lowering tohardtanh
asQConv2d
post operator.Test Plan
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler