[ET-VK] Don't specify memory layouts when testing #7322
Merged
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
As title. Now that we have a memory metadata tagging pass that automatically determines the optimal memory layout to use for operators, there is no need to specify what memory layout to test in the Python export tests. There were some issues with the memory metadata tagging pass when dealing with nodes that contain tensor lists, which have been fixed as part of this diff as well. Differential Revision: [D67180897](https://our.internmc.facebook.com/intern/diff/D67180897/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7322
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Cancelled JobAs of commit 060c7ea with merge base 0b1c1e5 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
SS-JIA
added a commit
that referenced
this pull request
Dec 13, 2024
As title. Now that we have a memory metadata tagging pass that automatically determines the optimal memory layout to use for operators, there is no need to specify what memory layout to test in the Python export tests. There were some issues with the memory metadata tagging pass when dealing with nodes that contain tensor lists, which have been fixed as part of this diff as well. Differential Revision: [D67180897](https://our.internmc.facebook.com/intern/diff/D67180897/) ghstack-source-id: 258028337 Pull Request resolved: #7322
|
This pull request was exported from Phabricator. Differential Revision: D67180897 |
junpi3
approved these changes
Dec 13, 2024
facebook-github-bot
merged commit 0859efb
into
gh/SS-JIA/155/base
43 of 49 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
SS-JIA
added a commit
that referenced
this pull request
Dec 13, 2024
As title. Now that we have a memory metadata tagging pass that automatically determines the optimal memory layout to use for operators, there is no need to specify what memory layout to test in the Python export tests. There were some issues with the memory metadata tagging pass when dealing with nodes that contain tensor lists, which have been fixed as part of this diff as well. Differential Revision: [D67180897](https://our.internmc.facebook.com/intern/diff/D67180897/) ghstack-source-id: 258028337 Pull Request resolved: #7322 Co-authored-by: Stephen Jia <[email protected]>
| (torch.rand(size=[1, 5, 2, 3]),), | ||
| memory_layouts=[vk_graph_schema.VkMemoryLayout.TENSOR_CHANNELS_PACKED], | ||
| ) | ||
|
|
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):
As title. Now that we have a memory metadata tagging pass that automatically determines the optimal memory layout to use for operators, there is no need to specify what memory layout to test in the Python export tests.
There were some issues with the memory metadata tagging pass when dealing with nodes that contain tensor lists, which have been fixed as part of this diff as well.
Differential Revision: D67180897