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
[Inductor] [Quant] Enable QLinear int8-mixed-bf16 Lowering #112486
[Inductor] [Quant] Enable QLinear int8-mixed-bf16 Lowering #112486
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/112486
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 08aceee with merge base eb15340 (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
ghstack-source-id: 2dda7766d50b605fb2f636dca6c4826065a459d5 Pull Request resolved: #112486
**Summary** - PR 6 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: efdd491d143e62dff0c001e3e93c25cd413aec9a Pull Request resolved: #112486
**Summary** - PR 6 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: 11d7c513dc9eceaa00cf9040fc19c0a2ab169052 Pull Request resolved: #112486
**Summary** - PR 6 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: 7b02bcb3054439cd276f14bf69d1f5cce96e4e27 Pull Request resolved: #112486
**Summary** - PR 6 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: 7b02bcb3054439cd276f14bf69d1f5cce96e4e27 Pull Request resolved: #112486
**Summary** - PR 7 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: 993d1e024cb473d02b1b0d081d3f1b11f2c51ccd Pull Request resolved: #112486
**Summary** - PR 7 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: 602000ad05296e6b255b0e00d72536aec19e26d7 Pull Request resolved: #112486
ghstack-source-id: 5dcf1b614cff856f96027bd9b6b1bde2635efd48 Pull Request resolved: #112486
**Summary** - PR 7 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: f761f79300d4759f60d7c72ce553378bfca801b0 Pull Request resolved: #112486
Hi @jgong5, please help take look of this PR also. |
if ( | ||
len(list(to_fp32_node.users)) != 1 | ||
or len(list(sub_node.users)) != 1 | ||
or len(list(mul_node.users)) != 1 | ||
): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think you should be able to match this in the pattern.
**Summary** - PR 7 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: d7da88230a860176f6c1587a4dc435b4b794c13d Pull Request resolved: #112486
@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 |
Merge failedReason: Command
Details for Dev Infra teamRaised by workflow job |
**Summary** - PR 7 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor #111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` 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: 4cde6e5121be8242b92ce943bf6244a6c4a3358a Pull Request resolved: #112486
@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 |
…12486) **Summary** - PR 7 for enabling Int8-Mixed-BF16 PT2E PTQ Quantization with Inductor pytorch#111640. - Enable the QLinear int8-mixed-bf16 weight prepack and post grad lowering inside inductor. **TestPlan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k test_qlinear ``` Pull Request resolved: pytorch#112486 Approved by: https://github.com/jgong5, https://github.com/eellison, https://github.com/jerryzh168
Stack from ghstack (oldest at bottom):
Summary
TestPlan
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler