Skip to content

[quant][graphmode][fix] Insert dequantize before use node#34411

Closed
jerryzh168 wants to merge 29 commits intogh/jerryzh168/242/basefrom
gh/jerryzh168/242/head
Closed

[quant][graphmode][fix] Insert dequantize before use node#34411
jerryzh168 wants to merge 29 commits intogh/jerryzh168/242/basefrom
gh/jerryzh168/242/head

Conversation

@jerryzh168
Copy link
Copy Markdown
Contributor

@jerryzh168 jerryzh168 commented Mar 7, 2020 •
edited
Loading

Stack from ghstack:

Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: D20519603

@jerryzh168
[quant][graphmode][fix] Insert dequantize before use node
d68ed95 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@jerryzh168 jerryzh168 requested a review from apaszke as a code owner March 7, 2020 01:41
This was referenced Mar 7, 2020
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
@facebook-github-bot facebook-github-bot added the oncall: jit Add this issue/PR to JIT oncall triage queue label Mar 7, 2020
@dr-ci
Copy link
Copy Markdown

dr-ci Bot commented Mar 7, 2020 •
edited
Loading

💊 CircleCI build failures summary and remediations

As of commit b03f558 (more details on the Dr. CI page):

  • 1/3 failures introduced in this PR

  • 2/3 broken upstream at merge base 11a4041 since Mar 21

    Please rebase on the viable/strict branch (expand for instructions)

    If your commit is newer than viable/strict, you can try basing on an older, stable commit:

    git fetch https://github.com/pytorch/pytorch viable/strict
git rebase --onto FETCH_HEAD $(git merge-base origin/master HEAD)

    If your commit is older than viable/strict:

    git fetch https://github.com/pytorch/pytorch viable/strict
git rebase FETCH_HEAD

    Check out the recency history of this "viable master" tracking branch.

🕵️ 1 new failure recognized by patterns

The following build failures do not appear to be due to upstream breakages:

See CircleCI build pytorch_macos_10_13_py3_test (1/1)

Step: "Test" (full log | pattern match details)

Mar 22 15:14:17 RuntimeError: test_jit_legacy failed! 
Mar 22 15:14:17 Ran 2438 tests in 236.944s 
Mar 22 15:14:17  
Mar 22 15:14:17 FAILED (failures=1, skipped=74, expected failures=1) 
Mar 22 15:14:17  
Mar 22 15:14:17 Generating XML reports... 
Mar 22 15:14:17 Traceback (most recent call last): 
Mar 22 15:14:17   File "test/run_test.py", line 682, in <module> 
Mar 22 15:14:17     main() 
Mar 22 15:14:17   File "test/run_test.py", line 675, in main 
Mar 22 15:14:17     raise RuntimeError(message) 
Mar 22 15:14:17 RuntimeError: test_jit_legacy failed! 
Mar 22 15:14:18 + cleanup 
Mar 22 15:14:18 + retcode=1 
Mar 22 15:14:18 + set +x

🚧 2 upstream failures:

These were probably caused by upstream breakages:

This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions on the GitHub issue tracker.

This comment has been revised 129 times.

@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
4b93255 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@jerryzh168 jerryzh168 mentioned this pull request Mar 7, 2020
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
0d40f1c 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
This was referenced Mar 10, 2020
Closed
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
d4735bd 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
b907cbe 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
This was referenced Mar 11, 2020
Closed
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
a423428 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
b47c43a 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
d95fb26 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
9579cea 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
b2a7811 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
2baf9f6 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
f83ffe2 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
aecf609 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
This was referenced Mar 19, 2020
Merged
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
dba3d11 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168 jerryzh168 mentioned this pull request Mar 20, 2020
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
567bebb 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
add4fe0 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
7cc3655 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
37695b0 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168 jerryzh168 mentioned this pull request Mar 20, 2020
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
1d95761 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@jerryzh168 jerryzh168 mentioned this pull request Mar 20, 2020
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
ba9cba5 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
This was referenced Mar 21, 2020
Closed
Closed
@jerryzh168
Update on "[quant][graphmode][fix] Insert dequantize before use node"
b03f558 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

Differential Revision: [D20519603](https://our.internmc.facebook.com/intern/diff/D20519603)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Copy Markdown
Contributor

facebook-github-bot commented Mar 23, 2020

This pull request has been merged in 28bf003.

@facebook-github-bot facebook-github-bot deleted the gh/jerryzh168/242/head branch March 27, 2020 14:16
okly366 pushed a commit to okly366/pytorch that referenced this pull request Apr 26, 2020
@jerryzh168
[quant][graphmode][fix] Insert dequantize before use node
02d762c 
Summary:
To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Reviewers:
.

Subscribers:

Tasks:

Tags:

ghstack-source-id: b613004
Pull Request resolved: pytorch/pytorch#34411
laurentdupin pushed a commit to laurentdupin/pytorch that referenced this pull request Apr 24, 2026
@jerryzh168 @facebook-github-bot
[quant][graphmode][fix] Insert dequantize before use node (pytorch#34411
ed7ba99 
)

Summary:
Pull Request resolved: pytorch#34411

To make sure dequantize and the node that uses the dequantized value reside in the
block, so that we can do quant fusion

Test Plan:
python test/test_jit.py

Imported from OSS

Differential Revision: D20519603

fbshipit-source-id: 3e4c68d0a73142716e19ea6a64ae3a5d6d51fa41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@apaszke apaszke Awaiting requested review from apaszke

@supriyar supriyar Awaiting requested review from supriyar

1 more reviewer

@z-a-f z-a-f z-a-f approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

Merged oncall: jit Add this issue/PR to JIT oncall triage queue

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@jerryzh168 @facebook-github-bot @supriyar @z-a-f @mruberry