[xnnpack][lite-int] Handle Constant Data #89445
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
Handling constant data for xnnpack delegation. This allows us to handle new modules like such:
```
class Module(torch.nn.Module):
def __init__(self):
super().__init__()
self._constant = torch.ones(4, 4, 4)
def forward(self, x):
return x + self._constant
```
this is the precursor work to handling convolution, as we need to serialize constant data(weights)
Differential Revision: [D41050349](https://our.internmc.facebook.com/intern/diff/D41050349/)
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/89445
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 60f0edf: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Handling constant data for xnnpack delegation. This allows us to handle new modules like such:
```
class Module(torch.nn.Module):
def __init__(self):
super().__init__()
self._constant = torch.ones(4, 4, 4)
def forward(self, x):
return x + self._constant
```
this is the precursor work to handling convolution, as we need to serialize constant data(weights)
Differential Revision: [D41050349](https://our.internmc.facebook.com/intern/diff/D41050349/)
[ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Nov 21, 2022
Pull Request resolved: #89445 Handling constant data for xnnpack delegation. This allows us to handle new modules like such: ``` class Module(torch.nn.Module): def __init__(self): super().__init__() self._constant = torch.ones(4, 4, 4) def forward(self, x): return x + self._constant ``` this is the precursor work to handling convolution, as we need to serialize constant data(weights) ghstack-source-id: 174132826 Differential Revision: [D41050349](https://our.internmc.facebook.com/intern/diff/D41050349/)
Contributor
|
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
Collaborator
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
kulinseth
pushed a commit
to kulinseth/pytorch
that referenced
this pull request
Dec 10, 2022
Handling constant data for xnnpack delegation. This allows us to handle new modules like such:
```
class Module(torch.nn.Module):
def __init__(self):
super().__init__()
self._constant = torch.ones(4, 4, 4)
def forward(self, x):
return x + self._constant
```
this is the precursor work to handling convolution, as we need to serialize constant data(weights)
Differential Revision: [D41050349](https://our.internmc.facebook.com/intern/diff/D41050349/)
Pull Request resolved: pytorch#89445
Approved by: https://github.com/digantdesai
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):
Handling constant data for xnnpack delegation. This allows us to handle new modules like such:
this is the precursor work to handling convolution, as we need to serialize constant data(weights)
Differential Revision: D41050349