Arm backend: qdq folding support for remaining operators #7340
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/7340
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 93c628e with merge base 5190106 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
oscarandersson8218
added
partner: arm
Collaborator
Author
Edge operators that are lowered to TOSA TABLEs are convereted to a custom edge IR table-op. Signed-off-by: Oscar Andersson <[email protected]> Change-Id: I147008c30b9b46c7b8ae1a1c15bc540fea614a69
This is a special case where node.args can be lists with many incoming dq-nodes. Signed-off-by: Oscar Andersson <[email protected]> Change-Id: Icf511a8bdeaaffb597b18455ab7f1fbd947ce3ca
Collaborator
|
Rebase pls |
Add support for q/dq folding of more operators such as hardtanh, maxpool2d, mul, relu, select, sub, to_copy. Signed-off-by: Oscar Andersson <[email protected]> Change-Id: Ifdabda4c927dade41c000859054696844c546f7b
sum is retraced to an int64 dtype of operator after q/dq folding. This patch adds a pass to manually force the dtype to be int8. Signed-off-by: Oscar Andersson <[email protected]> Change-Id: Ifa737a398c5a878d52cd76a2392499905da085ce
Add support for q/dq folding for the remaining supported ops in Arm backend. Signed-off-by: Oscar Andersson <[email protected]> Change-Id: I9012b4a501ce018c9771c729706be3b031a5c7ae
Signed-off-by: Oscar Andersson <[email protected]> Change-Id: Ibb17add461dc79e022a7f4accde29f9f9d61b16d
oscarandersson8218
force-pushed
the
qdq_folding
branch
from
93e7137 to
cdd6c91
Compare
Contributor
|
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Contributor
|
Some type checker issues (so far, still running) |
Address issues from pyre and add similar # pyre-ignores as in pytorch#7362. Signed-off-by: Oscar Andersson <[email protected]> Change-Id: I6feaa611dcd539b3b0d21a6a7dd696ef7db691ef
oscarandersson8218
force-pushed
the
qdq_folding
branch
from
cdd6c91 to
93c628e
Compare
freddan80
approved these changes
Jan 2, 2025
freddan80
approved these changes
Jan 7, 2025
Contributor
|
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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
Based on work in #7330, add support for qdq-folding of remaining operators.