[quant] Make choose_qparams_optimized return Tensors to preserve dtype #45530
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
Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Sep 29, 2020
Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: f315abb513eccf7f48f5720d07cc05cb18c5b712 Pull Request resolved: #45530
💊 CI failures summary and remediationsAs of commit 29e0d1c (more details on the Dr. CI page):
🚧 1 fixed upstream failure:These were probably caused by upstream breakages that were already fixed.
Please rebase on the
|
…eserve dtype" Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D24001134](https://our.internmc.facebook.com/intern/diff/D24001134) [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Sep 29, 2020
Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 807667faa1012387a82ef710ea63dc833071073c Pull Request resolved: #45530
…eserve dtype" Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D24001134](https://our.internmc.facebook.com/intern/diff/D24001134) [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Sep 29, 2020
Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 541687ce1372c1634f2fcaed64735a3ad073015f Pull Request resolved: #45530
dskhudia
approved these changes
Sep 30, 2020
| @@ -4437,7 +4437,7 @@ | |||
| use_c10_dispatcher: full | |||
| variants: function | |||
|
|
|||
| - func: choose_qparams_optimized(Tensor input, int numel, int n_bins, float ratio, int bit_width) -> (float, float) | |||
| - func: choose_qparams_optimized(Tensor input, int numel, int n_bins, float ratio, int bit_width) -> (Tensor, Tensor) | |||
There was a problem hiding this comment.
I was wondering the reason for having numel as an argument? Isn't it the same as input tensor size?
There was a problem hiding this comment.
Not necessarily, it could be per-channel in which case it will be numel per channel
…eserve dtype" Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D24001134](https://our.internmc.facebook.com/intern/diff/D24001134) [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Sep 30, 2020
Summary: Returning double values requires special handling as a return type for aten functions. Instead return tensors where the type is preserved in the tensor dtype Test Plan: python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 5077038980439051616348549ef5958654c23860 Pull Request resolved: #45530
|
This pull request has been merged in c112e89. |
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.
Stack from ghstack:
Summary:
Returning double values requires special handling as a return type for aten functions.
Instead return tensors where the type is preserved in the tensor dtype
Test Plan:
python test/test_quantization.py TestQuantizedTensor.test_choose_qparams_optimized
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D24001134