to make TIE quantized conv operator to fall back to hifi quantized conv op instead of cpu op for shapes not supported by the TIE kernel. #10770
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10770
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 2a4a73f with merge base 5ad676d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D74337713 |
zonglinpeng
approved these changes
May 8, 2025
|
@pytorchbot label "topic: not user facing" |
wl1026sun
force-pushed
the
export-D74337713
branch
from
ac2c959 to
6375850
Compare
wl1026sun
added a commit
to wl1026sun/executorch
that referenced
this pull request
May 8, 2025
…nv op instead of cpu op for shapes not supported by the TIE kernel. (pytorch#10770) Summary: some quantized conv shape are not supported by the TIE operator, right now the tie op will fall back to CPU op. with this diff would fall back to use the operator from the hifi non-tie backend instead. Reviewed By: zonglinpeng Differential Revision: D74337713
wl1026sun
added a commit
to wl1026sun/executorch
that referenced
this pull request
May 8, 2025
…nv op instead of cpu op for shapes not supported by the TIE kernel. (pytorch#10770) Summary: some quantized conv shape are not supported by the TIE operator, right now the tie op will fall back to CPU op. with this diff would fall back to use the operator from the hifi non-tie backend instead. Reviewed By: zonglinpeng Differential Revision: D74337713
wl1026sun
force-pushed
the
export-D74337713
branch
from
6375850 to
b7ba593
Compare
|
This pull request was exported from Phabricator. Differential Revision: D74337713 |
…nv op instead of cpu op for shapes not supported by the TIE kernel. (pytorch#10770) Summary: Pull Request resolved: pytorch#10770 some quantized conv shape are not supported by the TIE operator, right now the tie op will fall back to CPU op. with this diff would fall back to use the operator from the hifi non-tie backend instead. Reviewed By: zonglinpeng Differential Revision: D74337713
|
This pull request was exported from Phabricator. Differential Revision: D74337713 |
wl1026sun
force-pushed
the
export-D74337713
branch
from
b7ba593 to
2a4a73f
Compare
jhelsby
pushed a commit
to jhelsby/executorch
that referenced
this pull request
May 9, 2025
…nv op instead of cpu op for shapes not supported by the TIE kernel. Differential Revision: D74337713 Pull Request resolved: pytorch#10770
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.
Summary: some quantized conv shape are not supported by the TIE operator, right now the tie op will fall back to CPU op. with this diff would fall back to use the operator from the hifi non-tie backend instead.
Differential Revision: D74337713