qlinear: Remove legacy cpp_custom_type_hack support #72680
Closed
+10
−90
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
CI Flow Status⚛️ CI FlowRuleset - Version:
|
Contributor
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit cda6744 (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. |
Collaborator
|
@jerryzh168 can you take a look at this please? |
soulitzer
added
the
triaged
Ref pytorch#72263 for cpp_custom_type_hack removal `qlinear_prepack` and `qlinear_unpack` were updated to use torchbind and the `cpp_custom_type_hack` overloads marked with a deprecation warning in pytorch#38101 which was in the PyTorch 1.6 release. So, we are safe to break BC here.
peterbell10
force-pushed
the
qlinear_legacy_packing
branch
from
3ab4609 to
cda6744
Compare
Collaborator
Author
|
@jerryzh168 ping |
Contributor
|
@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 25, 2022
Summary: Ref #72263 for cpp_custom_type_hack removal `qlinear_prepack` and `qlinear_unpack` were updated to use torchbind and the `cpp_custom_type_hack` overloads marked with a deprecation warning in #38101 which was in the PyTorch 1.6 release. So, we are safe to break BC here. The deprecation warning only appears in unpack, but you can't use one without the other I think that's still okay. Pull Request resolved: #72680 Reviewed By: george-qi Differential Revision: D35056994 Pulled By: jerryzh168 fbshipit-source-id: cc046b9fa00d0219a4510854204564f4ea23da4b
Contributor
|
Hey @peterbell10. |
Contributor
|
@peterbell10 do we need to write BC-breaking notes for this one? |
shahofblah
pushed a commit
that referenced
this pull request
Mar 25, 2022
Summary: Ref #72263 for cpp_custom_type_hack removal `qlinear_prepack` and `qlinear_unpack` were updated to use torchbind and the `cpp_custom_type_hack` overloads marked with a deprecation warning in #38101 which was in the PyTorch 1.6 release. So, we are safe to break BC here. The deprecation warning only appears in unpack, but you can't use one without the other I think that's still okay. Pull Request resolved: #72680 Reviewed By: george-qi Differential Revision: D35056994 Pulled By: jerryzh168 fbshipit-source-id: cc046b9fa00d0219a4510854204564f4ea23da4b (cherry picked from commit 31abbf1)
Collaborator
Author
|
I've added a short note just in case. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 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.
Ref #72263 for cpp_custom_type_hack removal
qlinear_prepackandqlinear_unpackwere updated to use torchbindand the
cpp_custom_type_hackoverloads marked with a deprecationwarning in #38101 which was in the PyTorch 1.6 release. So, we are
safe to break BC here.
The deprecation warning only appears in unpack, but you can't use one
without the other I think that's still okay.
BC-breaking note
TorchScript models exported prior to PyTorch 1.6 using quantized linear operators will no longer work
TorchScipt models created with PyTorch 1.5 or earlier and using the operators
quantized::linear_prepack,quantized::linear_prepack_fp16,quantized::linear_unpack, orquantized::linear_unpack_fp16will no longer work and need to be re-exported.