Fix autograd engine checks and update InputMetadata #65235
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
[ghstack-poisoned]
Contributor
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 1fe42fd (more details on the Dr. CI page):
ci.pytorch.org: 1 failedThis comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
[ghstack-poisoned]
[ghstack-poisoned]
albanD
reviewed
Sep 17, 2021
Contributor
|
I'm letting Alban do full review on this. |
anjali411
commented
Sep 20, 2021
1. Updated the legacy type checks in `torch/csrc/autograd/engine.cpp` to individually validate the dtype, device, and layout equality for grad and tensor. 2. Removed device field from `InputMetadata` since it's already stored via storing options. Also, added `dtype()` and `layout()` methods to `InputMetadata`. To make this change, some calls had to be updated due to the change in constructor. 3. To fix #65016: a. Added a `is_tensor_subclass` field in `InputMetadata` to skip device checks for grad and tensor when the tensor has python key set on it (tensor subclass). [ghstack-poisoned]
1. Updated the legacy type checks in `torch/csrc/autograd/engine.cpp` to individually validate the dtype, device, and layout equality for grad and tensor. 2. Removed device field from `InputMetadata` since it's already stored via storing options. Also, added `dtype()` and `layout()` methods to `InputMetadata`. To make this change, some calls had to be updated due to the change in constructor. 3. To fix #65016: a. Added a `is_tensor_subclass` field in `InputMetadata` to skip device checks for grad and tensor when the tensor has python key set on it (tensor subclass). [ghstack-poisoned]
albanD
reviewed
Sep 20, 2021
Collaborator
albanD
left a comment
albanD
left a comment
There was a problem hiding this comment.
sgtm just the continue thing
1. Updated the legacy type checks in `torch/csrc/autograd/engine.cpp` to individually validate the dtype, device, and layout equality for grad and tensor. 2. Removed device field from `InputMetadata` since it's already stored via storing options. Also, added `dtype()` and `layout()` methods to `InputMetadata`. To make this change, some calls had to be updated due to the change in constructor. 3. To fix #65016: a. Added a `is_tensor_subclass` field in `InputMetadata` to skip device checks for grad and tensor when the tensor has python key set on it (tensor subclass). [ghstack-poisoned]
Contributor
Author
|
@anjali411 has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
1. Updated the legacy type checks in `torch/csrc/autograd/engine.cpp` to individually validate the dtype, device, and layout equality for grad and tensor. 2. Removed device field from `InputMetadata` since it's already stored via storing options. Also, added `dtype()` and `layout()` methods to `InputMetadata`. To make this change, some calls had to be updated due to the change in constructor. 3. To fix #65016: a. Added a `is_tensor_subclass` field in `InputMetadata` to skip device checks for grad and tensor when the tensor has python key set on it (tensor subclass). Differential Revision: [D31082693](https://our.internmc.facebook.com/intern/diff/D31082693) [ghstack-poisoned]
Contributor
Author
|
@anjali411 has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Contributor
|
@anjali411 merged this pull request in 9324d68. |
Contributor
|
This pull request has been reverted by 152f023. |
1. Updated the legacy type checks in `torch/csrc/autograd/engine.cpp` to individually validate the dtype, device, and layout equality for grad and tensor. 2. Removed device field from `InputMetadata` since it's already stored via storing options. Also, added `dtype()` and `layout()` methods to `InputMetadata`. To make this change, some calls had to be updated due to the change in constructor. 3. To fix #65016: a. Added a `is_tensor_subclass` field in `InputMetadata` to skip device checks for grad and tensor when the tensor has python key set on it (tensor subclass). Differential Revision: [D31082693](https://our.internmc.facebook.com/intern/diff/D31082693) [ghstack-poisoned]
Contributor
Author
|
@anjali411 has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Contributor
Author
Collaborator
|
I would say no since I don't think we plan to have broad subclassing support in 1.10 anyways? |
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:
torch/csrc/autograd/engine.cppto individually validate the dtype, device, and layout equality for grad and tensor.InputMetadatasince it's already stored via storing options. Also, addeddtype()andlayout()methods toInputMetadata. To make this change, some calls had to be updated due to the change in constructor.a. Added a
is_tensor_subclassfield inInputMetadatato skip device checks for grad and tensor when the tensor haspython key set on it (tensor subclass).
Differential Revision: D31117318