[ET-VK] Allow aten.cat.default to handle any number of input tensors#13226
[ET-VK] Allow aten.cat.default to handle any number of input tensors#13226facebook-github-bot merged 2 commits intogh/SS-JIA/273/basefrom
aten.cat.default to handle any number of input tensors#13226Conversation
## Context Previously, I updated the implementation of `aten.cat.default` in D76305343 (#11508) since the original implementation had a bug. The new implementation only supported up to 3 input tensors, but several models require the need for up to 6 input tensors. This diff updates the capabilities of the `concat` op so that any arbitrary number of input tensors may be accepted. ## Changes * Update implementation of the concat shader to be able to be called repeatedly, allowing support for any number of input tensors. Differential Revision: [D79893084](https://our.internmc.facebook.com/intern/diff/D79893084/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13226
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 2 Unrelated FailuresAs of commit 40c77e4 with merge base 0f70a5d ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D79893084 |
This PR needs a
|
| ([(S1, 3, 5), (S1, 4, 5)], 1), | ||
| ([(3, 5), (4, 5)], 0), | ||
| ([(3, 5), (4, 5), (1, 5)], 0), | ||
| ( |
There was a problem hiding this comment.
why is this input tuple formatted differently?
| ), | ||
| ] | ||
| ) | ||
| suite_inputs = [ |
There was a problem hiding this comment.
do you test somewhere else what what happens when invalid inputs are provided? i.e. can you gracefully handle wrong dimensions/incompatible shapes?
…nput tensors" ## Context Previously, I updated the implementation of `aten.cat.default` in D76305343 (#11508) since the original implementation had a bug. The new implementation only supported up to 3 input tensors, but several models require the need for up to 6 input tensors. This diff updates the capabilities of the `concat` op so that any arbitrary number of input tensors may be accepted. ## Changes * Update implementation of the concat shader to be able to be called repeatedly, allowing support for any number of input tensors. Differential Revision: [D79893084](https://our.internmc.facebook.com/intern/diff/D79893084/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D79893084 |
facebook-github-bot
merged commit 791683c
into
gh/SS-JIA/273/base
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
3 participants
Stack from ghstack (oldest at bottom):
aten.cat.defaultto handle any number of input tensors #13226Context
Previously, I updated the implementation of
aten.cat.defaultin D76305343 (#11508) since the original implementation had a bug. The new implementation only supported up to 3 input tensors, but several models require the need for up to 6 input tensors.This diff updates the capabilities of the
concatop so that any arbitrary number of input tensors may be accepted.Changes
Differential Revision: D79893084