add unsupported module list for partitioner #139
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
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D48667680 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D48667680 |
mcr229
force-pushed
the
export-D48667680
branch
from
7f2358d to
e7d9a1c
Compare
Differential Revision: D48667679 fbshipit-source-id: ca01aff1fdc7888e0abcb5a5437b0b6f2231dbd8
Differential Revision: D48667676 fbshipit-source-id: 19dc3ff786f6a57dd68102bf69acf2cb0e68363e
Summary: Pull Request resolved: pytorch/executorch#139 For Quantized Mobilenetv3. Right now decomposed hardswish and hardsigmoid gets partitioned with XNNPACKQuantizedPartitioner2, because they contain simple ops like add, mul, div, etc. These ops are all in FP32 since xnnpack doesn't support the quantized variants. Since we don't currently have support for a unified partition, we want to block the from our Quantized Partitioner. Reviewed By: digantdesai Differential Revision: D48667680 fbshipit-source-id: d055d4b7d5d0e0f0d3633635c16cfca7e6c5f48a
|
This pull request was exported from Phabricator. Differential Revision: D48667680 |
mcr229
force-pushed
the
export-D48667680
branch
from
e7d9a1c to
c5a4e0f
Compare
|
This pull request has been merged in 41125f9. |
Gasoonjia
pushed a commit
that referenced
this pull request
Jul 30, 2024
jirioc
pushed a commit
to nxp-upstream/executorch
that referenced
this pull request
May 14, 2025
…erter Merge in AITEC/executorch from feature/nxg10272/EIEX-292-add-support-for-aten.sigmoid-operator to main-nxp * commit 'a31f739ed1c851d6680c1b89a4b92c087e738d6f': Add implementation of Sigmoid operator converter
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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:
For Quantized Mobilenetv3.
Right now decomposed hardswish and hardsigmoid gets partitioned with XNNPACKQuantizedPartitioner2, because they contain simple ops like add, mul, div, etc.
These ops are all in FP32 since xnnpack doesn't support the quantized variants. Since we don't currently have support for a unified partition, we want to block the from our Quantized Partitioner.
Reviewed By: digantdesai
Differential Revision: D48667680