Change _generate_new_graph_signature #206
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
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D48917505 |
|
This pull request was exported from Phabricator. Differential Revision: D48917505 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D48917505 |
angelayi
force-pushed
the
export-D48917505
branch
from
ecabfe0 to
0ed9a2c
Compare
angelayi
added a commit
to angelayi/pytorch
that referenced
this pull request
Sep 5, 2023
Summary: X-link: pytorch/executorch#206 Previously `_generate_new_graph_signature` had the assumption that all transformations were not in place. However, this is an incorrect assumption leading to mysterious failures when running passes doing in-place modifications. This function is technically only needed in the case where the user output node or user input node name is changed. For example, if the user output node was "add" but a pass changes all the "add"s to "mul"s, then the output node will now be named "mul", which we have to update. For cases where users change the number of user inputs/outputs, number of parameters/buffers, or the names of parameters/buffers it will require extra work on the user's side to update the graph signature, since there is no automatic way for us to detect where to put what. Note: this doesn't actually change the names for the buffers_to_mutate part of the graph signature, but we're going to assume this is rare, because implementing auto-fixing for that is a little hard... Test Plan: Running `buck test fbcode//mode/dev-nosan fbcode//executorch/backends/xnnpack/test:` on top of D48710125, https://www.internalfb.com/intern/testinfra/testrun/5066549776877081 Differential Revision: D48917505
angelayi
force-pushed
the
export-D48917505
branch
from
0ed9a2c to
2914bfe
Compare
Summary: Pull Request resolved: pytorch/executorch#206 X-link: pytorch/pytorch#108571 Previously `_generate_new_graph_signature` had the assumption that all transformations were not in place. However, this is an incorrect assumption leading to mysterious failures when running passes doing in-place modifications. This function is technically only needed in the case where the user output node or user input node name is changed. For example, if the user output node was "add" but a pass changes all the "add"s to "mul"s, then the output node will now be named "mul", which we have to update. For cases where users change the number of user inputs/outputs, number of parameters/buffers, or the names of parameters/buffers it will require extra work on the user's side to update the graph signature, since there is no automatic way for us to detect where to put what. Note: this doesn't actually change the names for the buffers_to_mutate part of the graph signature, but we're going to assume this is rare, because implementing auto-fixing for that is a little hard... Reviewed By: digantdesai Differential Revision: D48917505 fbshipit-source-id: 53132c750ef4b0610fa0bb0fc4c944f4e6a2afc6
|
This pull request was exported from Phabricator. Differential Revision: D48917505 |
angelayi
force-pushed
the
export-D48917505
branch
from
2914bfe to
3272ad7
Compare
|
This pull request has been merged in f3c4edc. |
Gasoonjia
pushed a commit
that referenced
this pull request
Jul 30, 2024
* fix device int8 quant * fix duplicate device on linear int8 * typo * typo (missed comma made it a tuple) * missing fqn
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:
X-link: pytorch/pytorch#108571
Previously
_generate_new_graph_signaturehad the assumption that all transformations were not in place. However, this is an incorrect assumption leading to mysterious failures when running passes doing in-place modifications.This function is technically only needed in the case where the user output node or user input node name is changed. For example, if the user output node was "add" but a pass changes all the "add"s to "mul"s, then the output node will now be named "mul", which we have to update.
For cases where users change the number of user inputs/outputs, number of parameters/buffers, or the names of parameters/buffers it will require extra work on the user's side to update the graph signature, since there is no automatic way for us to detect where to put what.
Note: this doesn't actually change the names for the buffers_to_mutate part of the graph signature, but we're going to assume this is rare, because implementing auto-fixing for that is a little hard...
Differential Revision: D48917505