[quant][pt2e][bc-breaking] Set fold_quantize to True in convert_pt2e
#118701
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/118701
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit df455cb with merge base 46ef735 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D53247301 |
Summary: X-link: pytorch/pytorch#118701 This is a follow up to pytorch/pytorch#118605 to remove `fold_quantize` flag from `convert_pt2e` Differential Revision: D53247301
ed5f7ed to
ebf1404
Compare
|
This pull request was exported from Phabricator. Differential Revision: D53247301 |
Summary: X-link: pytorch/executorch#1766 This is a follow up to pytorch#118605 to remove `fold_quantize` flag from `convert_pt2e` Test Plan: CI Reviewed By: andrewor14 Differential Revision: D53247301
Summary: X-link: pytorch/pytorch#118701 This is a follow up to pytorch/pytorch#118605 to remove `fold_quantize` flag from `convert_pt2e` Reviewed By: andrewor14 Differential Revision: D53247301
ebf1404 to
df455cb
Compare
|
This pull request was exported from Phabricator. Differential Revision: D53247301 |
Summary: Pull Request resolved: #1766 X-link: pytorch/pytorch#118701 This is a follow up to pytorch/pytorch#118605 to set `fold_quantize` flag to True in `convert_pt2e` Reviewed By: andrewor14, digantdesai Differential Revision: D53247301 fbshipit-source-id: 5b2dbbc76487a8779f30c483b5ff4f054ba1ae8c
|
@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) |
Merge startedYour change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
fold_quantize to True in convert_pt2e
|
@pytorchbot revert -m="Diff reverted internally" -c="ghfirst" This Pull Request has been reverted by a revert inside Meta. To re-land this change, please open another pull request, assign the same reviewers, fix the CI failures that caused the revert and make sure that the failing CI runs on the PR by applying the proper ciflow label (e.g., ciflow/trunk).) |
|
@pytorchbot successfully started a revert job. Check the current status here. |
This reverts commit 482d952. Reverted #118701 on behalf of https://github.com/facebook-github-bot due to Diff reverted internally ([comment](#118701 (comment)))
|
@jerryzh168 your PR has been successfully reverted. |
Summary: This is a follow up to #118605 to remove `fold_quantize` flag from `convert_pt2e` Test Plan: CI Differential Revision: D53247301 BC Breaking Note: flag `fold_quantize` set to True `convert_pt2e` and now we'll fold the quantize op in the weight by default, so users will see model size reduction by default after pt2e quantization. 2.2 ``` folded_model = convert_pt2e(model, fold_quantize=True) non_folded_model = convert_pt2e(model) ``` 2.3 ``` folded_model = convert_pt2e(model) non_folded_model = convert_pt2e(model, fold_quantize=False) ``` Pull Request resolved: #118701 Approved by: https://github.com/andrewor14, https://github.com/leslie-fang-intel
This reverts commit 482d952. Reverted #118701 on behalf of https://github.com/facebook-github-bot due to Diff reverted internally ([comment](#118701 (comment)))
Summary: This is a follow up to #118605 to remove `fold_quantize` flag from `convert_pt2e` Test Plan: CI Differential Revision: D53247301 BC Breaking Note: flag `fold_quantize` set to True `convert_pt2e` and now we'll fold the quantize op in the weight by default, so users will see model size reduction by default after pt2e quantization. 2.2 ``` folded_model = convert_pt2e(model, fold_quantize=True) non_folded_model = convert_pt2e(model) ``` 2.3 ``` folded_model = convert_pt2e(model) non_folded_model = convert_pt2e(model, fold_quantize=False) ``` Pull Request resolved: #118701 Approved by: https://github.com/andrewor14, https://github.com/leslie-fang-intel
This reverts commit 482d952. Reverted #118701 on behalf of https://github.com/facebook-github-bot due to Diff reverted internally ([comment](#118701 (comment)))
Summary:
This is a follow up to #118605 to remove
fold_quantizeflag fromconvert_pt2eTest Plan: CI
Differential Revision: D53247301
BC Breaking Note:
flag
fold_quantizeset to Trueconvert_pt2eand now we'll fold the quantize op in the weight by default, so users will see model size reduction by default after pt2e quantization.2.2
2.3
cc @ezyang @gchanan @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler