[Quant] Implemented 4 bit embedding op support; added corresponding test case #69768
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
…est case Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags [ghstack-poisoned]
CI Flow Status⚛️ CI FlowRuleset - Version:
You can add a comment to the PR and tag @pytorchbot with the following commands: # ciflow rerun, "ciflow/default" will always be added automatically
@pytorchbot ciflow rerun
# ciflow rerun with additional labels "-l <ciflow/label_name>", which is equivalent to adding these labels manually and trigger the rerun
@pytorchbot ciflow rerun -l ciflow/scheduled -l ciflow/slowFor more information, please take a look at the CI Flow Wiki. |
dzdang
added a commit
that referenced
this pull request
Dec 10, 2021
…est case Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags ghstack-source-id: 318c8b8 Pull Request resolved: #69768
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit b908918 (more details on the Dr. CI page):
ci.pytorch.org: 1 failedThis comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
…esponding test case" Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags [ghstack-poisoned]
jerryzh168
reviewed
Dec 13, 2021
| torch.testing.assert_close(ref, qresult, atol=0.005, rtol=1e-3) | ||
|
|
||
| """ Tests the correctness of the quantized 4 bit embedding lookup operator """ | ||
| @given(num_embeddings=st.integers(10, 100), |
There was a problem hiding this comment.
is it possible to merge this test with test_embedding_byte?
also we don't want to use hypothesis for testing, might be good to remove hypothesis here as well and change it to simple for loops. (remove @given, example: https://github.com/pytorch/pytorch/blob/master/test/quantization/core/test_quantized_op.py#L1430), can be done in a separate PR.
There was a problem hiding this comment.
Do you mean removing hypothesis for both test_embedding_byte and test_embedding_4bit or just the latter? It was already there in test_embedding_byte, so I thought I was supposed to add it.
And yeah, I can easily combine test_embedding_byte and test_embedding_4bit. Is it acceptable to rename the function to something like test_embedding?
There was a problem hiding this comment.
Do you mean removing hypothesis for both test_embedding_byte and test_embedding_4bit or just the latter? It was already there in test_embedding_byte, so I thought I was supposed to add it.
we can combine the tests and remove hypothesis, it can be in a separate PR
There was a problem hiding this comment.
Sounds good. I'll put that in PR5
jerryzh168
approved these changes
Dec 13, 2021
…esponding test case" Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags [ghstack-poisoned]
…esponding test case" Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags [ghstack-poisoned]
|
please import the PR with ghimport |
…esponding test case" Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags [ghstack-poisoned]
…esponding test case" Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Test plan: In pytorch main dir, execute ``` python test/test_quantization.py TestStaticQuantizedModule.test_embedding_api ``` to run the series of tests, including the newly added test_embedding_4bit function Tasks: T106931792 Tags [ghstack-poisoned]
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
dzdang
added a commit
that referenced
this pull request
Jan 27, 2022
…roduced by #69768" Differential Revision: [D33808593](https://our.internmc.facebook.com/intern/diff/D33808593) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Jan 27, 2022
Differential Revision: [D33808593](https://our.internmc.facebook.com/intern/diff/D33808593) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Jan 28, 2022
…roduced by #69768" Differential Revision: [D33808593](https://our.internmc.facebook.com/intern/diff/D33808593) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Jan 28, 2022
Differential Revision: [D33808593](https://our.internmc.facebook.com/intern/diff/D33808593) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Jan 28, 2022
…roduced by #69768" Differential Revision: [D33808593](https://our.internmc.facebook.com/intern/diff/D33808593) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Jan 28, 2022
Differential Revision: [D33808593](https://our.internmc.facebook.com/intern/diff/D33808593) [ghstack-poisoned]
facebook-github-bot
pushed a commit
that referenced
this pull request
Jan 28, 2022
cyyever
pushed a commit
to cyyever/pytorch_private
that referenced
this pull request
Feb 3, 2022
…69768 (#71387) Summary: Pull Request resolved: pytorch/pytorch#71387 Test Plan: Imported from OSS Reviewed By: albanD Differential Revision: D33808593 Pulled By: dzdang fbshipit-source-id: 3950400dc7506006666fcd055819e9a08a42eda9 (cherry picked from commit 38dc2de)
cyyever
pushed a commit
to cyyever/pytorch_private
that referenced
this pull request
Feb 3, 2022
…69768 (#71387) Summary: Pull Request resolved: pytorch/pytorch#71387 Test Plan: Imported from OSS Reviewed By: albanD Differential Revision: D33808593 Pulled By: dzdang fbshipit-source-id: 3950400dc7506006666fcd055819e9a08a42eda9 (cherry picked from commit 38dc2de)
cyyever
pushed a commit
to cyyever/pytorch_private
that referenced
this pull request
Feb 9, 2022
…69768 (#71387) Summary: Pull Request resolved: pytorch/pytorch#71387 Test Plan: Imported from OSS Reviewed By: albanD Differential Revision: D33808593 Pulled By: dzdang fbshipit-source-id: 3950400dc7506006666fcd055819e9a08a42eda9 (cherry picked from commit 38dc2de)
cyyever
pushed a commit
to cyyever/pytorch_private
that referenced
this pull request
Feb 9, 2022
…69768 (#71387) Summary: Pull Request resolved: pytorch/pytorch#71387 Test Plan: Imported from OSS Reviewed By: albanD Differential Revision: D33808593 Pulled By: dzdang fbshipit-source-id: 3950400dc7506006666fcd055819e9a08a42eda9 (cherry picked from commit 38dc2de)
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:
Summary: Support for the 4 embedding operator has been added. The support is analogous to the preexisting support for byte/8bit embedding. A corresponding test case was added to test_quantized_embedding_op.py
Reviewers: jerryzh168
Subscribers: jerryzh168, supriyar
Test plan: In pytorch main dir, execute
to run the series of tests, including the newly added test_embedding_4bit
function
Tasks: T106931792
Tags
Differential Revision: D33152673