-
Notifications
You must be signed in to change notification settings - Fork 26.3k
[Quant][core][refactorization] Refactored qlinear_unpack.cpp into an implementation file and higher level call registration and definition file #73956
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
Conversation
…implementation file and higher level call registration and definition file Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
CI Flow Status⚛️ CI FlowRuleset - Version:
|
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 8557ad0 (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
jerryzh168
left a comment
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.
looks great!
|
we should have |
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. [ghstack-poisoned]
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. Test plan: ``` python test/test_quantization.py ``` Differential Revision: [D34824249](https://our.internmc.facebook.com/intern/diff/D34824249) [ghstack-poisoned]
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
…pp into an implementation file and higher level call registration and definition file" Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. Test plan: ``` python test/test_quantization.py ``` Differential Revision: [D34824249](https://our.internmc.facebook.com/intern/diff/D34824249) [ghstack-poisoned]
…implementation file and higher level call registration and definition file Summary: This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. Test plan: ``` python test/test_quantization.py ``` ghstack-source-id: f12e590 Pull Request resolved: #73956
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
…implementation file and higher level call registration and definition file (#73956) Summary: Pull Request resolved: #73956 This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. Test Plan: ``` python test/test_quantization.py ``` Imported from OSS Differential Revision: D34824249 D34824249 Reviewed By: ezyang Pulled By: dzdang fbshipit-source-id: 5d33c16dde7f9c7606a26802855094bea4757867
|
Hey @dzdang. |
…ytorch#74526) Summary: Pull Request resolved: pytorch#74526 PR pytorch#73956 refactored `qlinear_unpack.cpp` and moved it out from the build system. Hence `TORCH_LIBRARY_IMPL` for `qlinear_unpack` ops are missing from the build. This PR adds it back. Test Plan: CI Differential Revision: D35039381 fbshipit-source-id: e633a7cc8cd85bfccfcb6152c144106d2403b679
…74526) Summary: Pull Request resolved: #74526 PR #73956 refactored `qlinear_unpack.cpp` and moved it out from the build system. Hence `TORCH_LIBRARY_IMPL` for `qlinear_unpack` ops are missing from the build. This PR adds it back. Test Plan: CI Reviewed By: dzdang Differential Revision: D35039381 fbshipit-source-id: 86f728f15ec8db25445215c34434a05b11c80e3f
…74526) Summary: Pull Request resolved: #74526 PR #73956 refactored `qlinear_unpack.cpp` and moved it out from the build system. Hence `TORCH_LIBRARY_IMPL` for `qlinear_unpack` ops are missing from the build. This PR adds it back. Test Plan: CI Reviewed By: dzdang Differential Revision: D35039381 fbshipit-source-id: 86f728f15ec8db25445215c34434a05b11c80e3f (cherry picked from commit 9cf8c4c)
…implementation file and higher level call registration and definition file (#73956) Summary: Pull Request resolved: #73956 This refactorization is analogous to the one done in #73773, but for linear instead of conv. Refer to the summary in that PR for details. Test Plan: ``` python test/test_quantization.py ``` Imported from OSS Differential Revision: D34824249 D34824249 Reviewed By: ezyang Pulled By: dzdang fbshipit-source-id: 5d33c16dde7f9c7606a26802855094bea4757867 (cherry picked from commit b1ab945)
…74526) Summary: Pull Request resolved: #74526 PR #73956 refactored `qlinear_unpack.cpp` and moved it out from the build system. Hence `TORCH_LIBRARY_IMPL` for `qlinear_unpack` ops are missing from the build. This PR adds it back. Test Plan: CI Reviewed By: dzdang Differential Revision: D35039381 fbshipit-source-id: 86f728f15ec8db25445215c34434a05b11c80e3f (cherry picked from commit 9cf8c4c)
Stack from ghstack (oldest at bottom):
Summary:
This refactorization is analogous to the one done in #73773, but for linear instead of conv.
Refer to the summary in that PR for details.
Test plan:
Differential Revision: D34824249