Renaming quantize to quantize_
#467
Merged
Conversation
This file contains 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/467
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 79e740c with merge base 5d22ad2 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
requested review from
msaroufim,
HDCharles,
gau-nernst,
andrewor14 and
jcaip
msaroufim
reviewed
Jul 2, 2024
| @@ -74,7 +74,7 @@ from torchao.quantization.quant_primitives import MappingType, ZeroPointDomain | |||
| from torchao.dtypes import to_affine_quantized | |||
There was a problem hiding this comment.
The main README still has quantize listed, mind doing a comprehensive code search?
Summary: Addressing feedback for `quantize` API from pytorch#391 (comment) this is an API that changes model inplace, so we want to change the name to reflect that. inplace model quantization is important especially for LLM since it will be hard to load the model to memory. we typically load the model to meta device and then load the quantized weight. Test Plan: python test/quantization/test_quant_api.py python test/integration/test_integration.py Reviewers: Subscribers: Tasks: Tags:
msaroufim
approved these changes
Jul 3, 2024
gau-nernst
reviewed
Jul 3, 2024
gau-nernst
approved these changes
Jul 3, 2024
malfet
approved these changes
Jul 3, 2024
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
Summary: Addressing feedback for `quantize` API from pytorch#391 (comment) this is an API that changes model inplace, so we want to change the name to reflect that. inplace model quantization is important especially for LLM since it will be hard to load the model to memory. we typically load the model to meta device and then load the quantized weight. Test Plan: python test/quantization/test_quant_api.py python test/integration/test_integration.py Reviewers: Subscribers: Tasks: Tags:
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
Addressing feedback for
quantizeAPI from #391 (comment)this is an API that changes model inplace, so we want to change the name to reflect that. inplace model quantization is important especially for LLM since it will be hard to load the model to memory. we typically load the model to meta device and then load the quantized weight.
Test Plan:
python test/quantization/test_quant_api.py
python test/integration/test_integration.py
Reviewers:
Subscribers:
Tasks:
Tags: