[quant][fx] Add support for matching multiple arguments in patterns #89986
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
Summary: This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype Test Plan: python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/89986
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 3b06dbd: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
… patterns" Summary: This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype Test Plan: python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args Reviewers: Subscribers: Tasks: Tags: cc jianyuh raghuramank100 jamesr66a vkuzo jgong5 Xia-Weiwen leslie-fang-intel [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Dec 1, 2022
Summary: This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype Test Plan: python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: d567c7b Pull Request resolved: #89986
vkuzo
approved these changes
Dec 1, 2022
| self.checkGraphModuleNodes(m_ref, expected_node_occurrence=node_occurrence_ref) | ||
|
|
||
| def test_match_pattern_with_multiple_args(self): | ||
| """ Test that we can match a pattern that has multiple arguments |
There was a problem hiding this comment.
what does "multiple arguments" mean?
There was a problem hiding this comment.
this means reshape has multiple arguments, also added in the docstring
| return transpose | ||
|
|
||
| backend_pattern_configs.append( | ||
| BackendPatternConfig((torch.reshape, torch.transpose, MatchAllNode)) |
There was a problem hiding this comment.
this looks like a pattern of a -> b -> c, could we explain what specifically is different about this compare to what's already supported?
There was a problem hiding this comment.
this means a(b(input1), c(input2)) actually, sure, I'll add more explanations
… patterns"
Summary:
This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype
Before this PR, we only support patterns like:
```
x -> conv -> bn -> relu
(relu, (bn, conv))
```
where each operator has a single node, the code breaks when we want to match a pattern that has an op that has multiple arguments, such as:
```
shape \
transpose -> reshape -> output ->
```
where `reshape` has two arguments
Test Plan:
python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args
Reviewers:
Subscribers:
Tasks:
Tags:
cc jianyuh raghuramank100 jamesr66a vkuzo jgong5 Xia-Weiwen leslie-fang-intel
[ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Dec 1, 2022
Summary: This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype Test Plan: python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: ae6e866 Pull Request resolved: #89986
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
kulinseth
pushed a commit
to kulinseth/pytorch
that referenced
this pull request
Dec 10, 2022
…ytorch#89986) Summary: This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype Before this PR, we only support patterns like: ``` x -> conv -> bn -> relu (relu, (bn, conv)) ``` where each operator has a single node, the code breaks when we want to match a pattern that has an op that has multiple arguments, such as: ``` shape \ transpose -> reshape -> output -> ``` where `reshape` has two arguments Test Plan: python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args Reviewers: Subscribers: Tasks: Tags: Pull Request resolved: pytorch#89986 Approved by: https://github.com/vkuzo
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
Stack from ghstack (oldest at bottom):
Summary:
This PR adds support for matching patterns that has multiple arguments, it's needed for quantization in PyTorch 2.0 early prototype
Before this PR, we only support patterns like:
where each operator has a single node, the code breaks when we want to match a pattern that has an op that has multiple arguments, such as:
where
reshapehas two argumentsTest Plan:
python test/test_quantization.py TestQuantizeFx.test_match_pattern_with_multiple_args
Reviewers:
Subscribers:
Tasks:
Tags:
cc @jianyuh @raghuramank100 @jamesr66a @vkuzo @jgong5 @Xia-Weiwen @leslie-fang-intel