Skip to content

[reland] Add int1 to int7 dtypes#137928

Closed
jerryzh168 wants to merge 5 commits into
gh/jerryzh168/854/basefrom
gh/jerryzh168/854/head
Closed

[reland] Add int1 to int7 dtypes#137928
jerryzh168 wants to merge 5 commits into
gh/jerryzh168/854/basefrom
gh/jerryzh168/854/head

Conversation

@jerryzh168

@jerryzh168 jerryzh168 commented Oct 14, 2024

Copy link
Copy Markdown
Contributor

Stack from ghstack (oldest at bottom):

Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: D64344944

Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@pytorch-bot

pytorch-bot Bot commented Oct 14, 2024

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/137928

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 6cf187b with merge base a1b22e3 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@pytorch-bot pytorch-bot Bot added the release notes: quantization release notes category label Oct 14, 2024
jerryzh168 added a commit that referenced this pull request Oct 14, 2024
Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: 9979fb5
Pull Request resolved: #137928
@jerryzh168

Copy link
Copy Markdown
Contributor Author

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@vadimkantorov

Copy link
Copy Markdown
Contributor

Are these to represent signed dtypes? (trying to understand the semantic difference between uint1 and int1 - or maybe it's just for simplicity in coding to have also "signed" dtypes?)

Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D64344944](https://our.internmc.facebook.com/intern/diff/D64344944)

[ghstack-poisoned]
@jerryzh168

Copy link
Copy Markdown
Contributor Author

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@jerryzh168

Copy link
Copy Markdown
Contributor Author

Are these to represent signed dtypes? (trying to understand the semantic difference between uint1 and int1 - or maybe it's just for simplicity in coding to have also "signed" dtypes?)

yes, these are for signed dtypes

@malfet malfet left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure, though please consider dropping Int1, not a very useful type imo

@pytorch-bot pytorch-bot Bot added the ciflow/trunk Trigger trunk jobs on your pull request label Oct 14, 2024
@jerryzh168

Copy link
Copy Markdown
Contributor Author

Sure, though please consider dropping Int1, not a very useful type imo

yeah I thought about this as well, seems like edge wants to add it still, cc @metascroy and @kimishpatel

@kimishpatel

Copy link
Copy Markdown
Contributor

Sure, though please consider dropping Int1, not a very useful type imo

yeah I thought about this as well, seems like edge wants to add it still, cc @metascroy and @kimishpatel

Unless int1 significantly adds maintenance burden, I think we should have it for completeness given we have uint1 as well.

@malfet

malfet commented Oct 15, 2024

Copy link
Copy Markdown
Contributor

@pytorchbot rebase

@pytorchmergebot

Copy link
Copy Markdown
Collaborator

@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here

[ghstack-poisoned]
@pytorchmergebot

Copy link
Copy Markdown
Collaborator

Successfully rebased gh/jerryzh168/854/orig onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via ghstack checkout https://github.com/pytorch/pytorch/pull/137928)

pytorchmergebot pushed a commit that referenced this pull request Oct 15, 2024
Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: ac4d8f7
Pull Request resolved: #137928
@jerryzh168

Copy link
Copy Markdown
Contributor Author

cc @malfet I will need to resolve the errors in the diff before landing btw, still fixing some of these

Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D64344944](https://our.internmc.facebook.com/intern/diff/D64344944)

[ghstack-poisoned]
@jerryzh168

Copy link
Copy Markdown
Contributor Author

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D64344944](https://our.internmc.facebook.com/intern/diff/D64344944)

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Oct 16, 2024
Summary:
Similar to #117208, we want to add int1 to int7 for edge use cases
for weight quantization

Test Plan:
python test/test_quantization.py -k test_uint4_int4_dtype

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: 7072938
Pull Request resolved: #137928
@jerryzh168

Copy link
Copy Markdown
Contributor Author

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@jerryzh168

Copy link
Copy Markdown
Contributor Author

@pytorchbot merge

@pytorchmergebot

Copy link
Copy Markdown
Collaborator

Merge failed

Reason: This PR has internal changes and must be landed via Phabricator! Please try reimporting/rexporting the PR!

Details for Dev Infra team Raised by workflow job

@facebook-github-bot

Copy link
Copy Markdown
Contributor

@pytorchbot merge

(Initiating merge automatically since Phabricator Diff has merged)

@pytorchmergebot

Copy link
Copy Markdown
Collaborator

Merge started

Your 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

Advanced Debugging
Check the merge workflow status
here

@github-actions github-actions Bot deleted the gh/jerryzh168/854/head branch November 17, 2024 02:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ciflow/trunk Trigger trunk jobs on your pull request Merged release notes: quantization release notes category

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants