[Quant] Make quantizable LSTM scriptable #83304
Closed
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
Summary: Previously `torch.nn.quantizable.LSTM` was not scriptable due to (1) the use of asterisk to unpack arguments, and (2) some arguments being Optional, which was not understood by setitem. This commit resolves both of these issues, enabling LSTM quantized through custom modules to work with TorchScript. Test Plan: python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm Reviewers: jerryzh, z-a-f Subscribers: jerryzh, z-a-f, supriyar Tasks: #83211 #75042 [ghstack-poisoned]
andrewor14
requested review from
albanD,
jbschlosser and
saketh-are
as code owners
🔗 Helpful links
✅ No Failures (0 Pending)As of commit 7f5745b (more details on the Dr. CI page): Expand to see more💚 💚 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. |
Summary: Previously `torch.nn.quantizable.LSTM` was not scriptable due to (1) the use of asterisk to unpack arguments, and (2) some arguments being Optional, which was not understood by setitem. This commit resolves both of these issues, enabling LSTM quantized through custom modules to work with TorchScript. Test Plan: python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm Reviewers: jerryzh168, z-a-f Subscribers: jerryzh168, z-a-f, supriyar Tasks: #83211 #75042 [ghstack-poisoned]
Summary: Previously `torch.nn.quantizable.LSTM` was not scriptable due to (1) the use of asterisk to unpack arguments, and (2) some arguments being Optional, which was not understood by setitem. This commit resolves both of these issues, enabling LSTM quantized through custom modules to work with TorchScript. Test Plan: python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm Reviewers: jerryzh168, z-a-f Subscribers: jerryzh168, z-a-f, supriyar Tasks: #83211 #75042 [ghstack-poisoned]
Summary: Previously `torch.nn.quantizable.LSTM` was not scriptable due to (1) the use of asterisk to unpack arguments, and (2) some arguments being Optional, which was not understood by setitem. This commit resolves both of these issues, enabling LSTM quantized through custom modules to work with TorchScript. Test Plan: python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm Reviewers: jerryzh168, z-a-f Subscribers: jerryzh168, z-a-f, supriyar Tasks: #83211 #75042 [ghstack-poisoned]
andrewor14
added a commit
that referenced
this pull request
Aug 11, 2022
Summary: Previously `torch.nn.quantizable.LSTM` was not scriptable due to (1) the use of asterisk to unpack arguments, and (2) some arguments being Optional, which was not understood by setitem. This commit resolves both of these issues, enabling LSTM quantized through custom modules to work with TorchScript. Test Plan: python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm Reviewers: jerryzh168, z-a-f Subscribers: jerryzh168, z-a-f, supriyar Tasks: #83211 #75042 ghstack-source-id: ee4e281 Pull Request resolved: #83304
jerryzh168
approved these changes
Aug 11, 2022
|
@pytorchbot merge |
|
@pytorchbot successfully started a merge job. Check the current status here. |
|
Hey @andrewor14. |
andrewor14
added
release notes: quantization
facebook-github-bot
pushed a commit
that referenced
this pull request
Aug 12, 2022
Summary: Previously `torch.nn.quantizable.LSTM` was not scriptable due to (1) the use of asterisk to unpack arguments, and (2) some arguments being Optional, which was not understood by setitem. This commit resolves both of these issues, enabling LSTM quantized through custom modules to work with TorchScript. Pull Request resolved: #83304 Approved by: https://github.com/jerryzh168 Test Plan: contbuild & OSS CI, see https://hud.pytorch.org/commit/pytorch/pytorch/f81b4ae55cf4d9b44641178f31fd713f65d5af2e Test plan from GitHub: python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm Reviewed By: atalman Differential Revision: D38658671 Pulled By: andrewor14 fbshipit-source-id: 5091e6e1edc91f82bb26bc91b020b9997b17e07e
This was referenced Aug 26, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Stack from ghstack (oldest at bottom):
Summary: Previously
torch.nn.quantizable.LSTMwas not scriptabledue to (1) the use of asterisk to unpack arguments, and (2) some
arguments being Optional, which was not understood by setitem.
This commit resolves both of these issues, enabling LSTM quantized
through custom modules to work with TorchScript.
Test Plan:
python test/test_quantization.py TestQuantizedOps.test_custom_module_lstm
Reviewers: jerryzh168, z-a-f
Subscribers: jerryzh168, z-a-f, supriyar
Tasks:
#83211
#75042