[Quant] [PT2] Enable QLinear input with multi dims #113733
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
[ghstack-poisoned]
leslie-fang-intel
requested review from
digantdesai,
jerryzh168,
jianyuh,
kimishpatel and
salilsdesai
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/113733
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 29479ce with merge base 7bbc19a ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
github-actions
bot
added
the
module: cpu
leslie-fang-intel
changed the title
|
cc @jianan-gu |
jgong5
requested changes
Nov 16, 2023
**Summary** Previously QLinear implementation assumes inputs is with dim of 2. In this diff, we make QLinear accepts input of dim more than 2 with input and output reshape. **Test Plan** ``` python -u -m pytest -s -v test_quantized_op.py -k test_qlinear_pt2e ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
jgong5
approved these changes
Nov 17, 2023
**Summary** In the previous QLinear implementation, it was assumed that inputs have a dimension of 2. In this update, we have modified QLinear to accept inputs with a dimension greater than 2, incorporating input and output reshaping accordingly. **Test Plan** ``` python -u -m pytest -s -v test_quantized_op.py -k test_qlinear_pt2e ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 voznesenskym penguinwu EikanWang Guobing-Chen zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Nov 17, 2023
ghstack-source-id: b1796d3 Pull Request resolved: pytorch#113733
**Summary** In the previous QLinear implementation, it was assumed that inputs have a dimension of 2. In this update, we have modified QLinear to accept inputs with a dimension greater than 2, incorporating input and output reshaping accordingly. **Test Plan** ``` python -u -m pytest -s -v test_quantized_op.py -k test_qlinear_pt2e ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 voznesenskym penguinwu EikanWang Guobing-Chen zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Nov 20, 2023
ghstack-source-id: 7fd173b Pull Request resolved: pytorch#113733
|
Hi @jerryzh168, could you kindly help to take a look of this PR? |
eellison
approved these changes
Nov 27, 2023
**Summary** In the previous QLinear implementation, it was assumed that inputs have a dimension of 2. In this update, we have modified QLinear to accept inputs with a dimension greater than 2, incorporating input and output reshaping accordingly. **Test Plan** ``` python -u -m pytest -s -v test_quantized_op.py -k test_qlinear_pt2e ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 voznesenskym penguinwu EikanWang Guobing-Chen zhuhaozhe blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 aakhundov ColinPeppler [ghstack-poisoned]
|
@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 |
pytorchmergebot
pushed a commit
that referenced
this pull request
Dec 6, 2023
…on size exceeds 2 (#113912) **Summary** When decomposing `Linear` to `addmm` or `mm` within Inductor, if the input dimension size exceeds 2, `reshape` nodes are introduced to convert the input into a 2-dimensional form before and after the `addmm` or `mm` node. It is essential to identify and match this pattern during quantization for dequantization promotion. For instance, ``` # quant # + - - - | - - - + # | dequant | # | | | # | reshape | # | / \ | # | node1 node2 | # + - | - - - | - + # reshape reshape # + - | - - - | - + # quant quant ``` In this PR, we mainly do 2 things: - Extend support for the dequantization pattern in QLinear when the input dimension size exceeds 2. - Revise the implementation of the dequant promotion pass, as it now needs to accommodate the matching of four different patterns. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k input_dim_exceeds_2 ``` Pull Request resolved: #113912 Approved by: https://github.com/jgong5, https://github.com/eellison ghstack dependencies: #113733
pytorchmergebot
pushed a commit
that referenced
this pull request
Dec 6, 2023
… size exceeds 2 (#113928) **Summary** Enable the qlinear weight prepack when input dimension size exceeds 2. There are extra reshape node before and after the `addmm` or `mm` node if input dimension size exceeds 2. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k input_dim_exceeds_2 ``` Pull Request resolved: #113928 Approved by: https://github.com/jgong5, https://github.com/eellison ghstack dependencies: #113733, #113912
dmenig
pushed a commit
to dmenig/pytorch
that referenced
this pull request
Dec 21, 2023
**Summary** In the previous QLinear implementation, it was assumed that inputs have a dimension of 2. In this update, we have modified QLinear to accept inputs with a dimension greater than 2, incorporating input and output reshaping accordingly. **Test Plan** ``` python -u -m pytest -s -v test_quantized_op.py -k test_qlinear_pt2e ``` Pull Request resolved: pytorch#113733 Approved by: https://github.com/jgong5, https://github.com/eellison
dmenig
pushed a commit
to dmenig/pytorch
that referenced
this pull request
Dec 21, 2023
…on size exceeds 2 (pytorch#113912) **Summary** When decomposing `Linear` to `addmm` or `mm` within Inductor, if the input dimension size exceeds 2, `reshape` nodes are introduced to convert the input into a 2-dimensional form before and after the `addmm` or `mm` node. It is essential to identify and match this pattern during quantization for dequantization promotion. For instance, ``` # quant # + - - - | - - - + # | dequant | # | | | # | reshape | # | / \ | # | node1 node2 | # + - | - - - | - + # reshape reshape # + - | - - - | - + # quant quant ``` In this PR, we mainly do 2 things: - Extend support for the dequantization pattern in QLinear when the input dimension size exceeds 2. - Revise the implementation of the dequant promotion pass, as it now needs to accommodate the matching of four different patterns. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k input_dim_exceeds_2 ``` Pull Request resolved: pytorch#113912 Approved by: https://github.com/jgong5, https://github.com/eellison ghstack dependencies: pytorch#113733
dmenig
pushed a commit
to dmenig/pytorch
that referenced
this pull request
Dec 21, 2023
… size exceeds 2 (pytorch#113928) **Summary** Enable the qlinear weight prepack when input dimension size exceeds 2. There are extra reshape node before and after the `addmm` or `mm` node if input dimension size exceeds 2. **Test Plan** ``` python -m pytest test_mkldnn_pattern_matcher.py -k input_dim_exceeds_2 ``` Pull Request resolved: pytorch#113928 Approved by: https://github.com/jgong5, https://github.com/eellison ghstack dependencies: pytorch#113733, pytorch#113912
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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
In the previous QLinear implementation, it was assumed that inputs have a dimension of 2. In this update, we have modified QLinear to accept inputs with a dimension greater than 2, incorporating input and output reshaping accordingly.
Test Plan
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10 @voznesenskym @penguinwu @EikanWang @Guobing-Chen @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler