[ET] enabling half dtype input for quantization #11479
Merged
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
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11479
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 New Failures, 1 Cancelled JobAs of commit 316d2c0 with merge base 8cfa858 ( NEW FAILURES - The following jobs have failed:
CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced Jun 9, 2025
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
This was referenced Jun 11, 2025
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76053764 |
facebook-github-bot
merged commit 1f024fc
into
gh/ahmtox/12/base
92 of 98 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
ahmtox
added a commit
that referenced
this pull request
Jun 16, 2025
Summary: # Context Need these changes that were reverted in the weekend. Original stack of commits were unable to be merged into main due to an existing lintrunner issue blocking the merge. All the changes already went through [review](#11479) and approved. Differential Revision: D76737404
SS-JIA
added a commit
that referenced
this pull request
Aug 6, 2025
Pull Request resolved: #11479 Currently the cpu implementation for the quantization operator (which includes `quantize_per_token`, `quantize_per_tensor`, and `quantize_per_channel`), does not inherently support half (fp16) input scalar types. In order to align with the PyTorch implementation that accepts fp16 and bfp16 inputs, this diff aims to enable half input dtype support for the quantization operators. We will be comparing this implementation against the vulkan operators. As defined in ExecuTorch [scalar_type_util.h](https://github.com/pytorch/executorch/blob/053686242c1687f0d51b3bb8befd14b047d7b025/runtime/core/exec_aten/util/scalar_type_util.h#L190) file, there is a method to enable support simply changing which preprocessor is called to ET_FORALL_FLOATH_TYPES. This enables support for Half (fp16), Float (fp32), and Double (fp64). I have also included more comprehensive testing against the input dtypes, including adding double testing since it didn't already exist before. Instead of just confirming that all the output dtypes are supported, we also have a check that all input dtypes are supported now as well. ghstack-source-id: 290376481 @exported-using-ghexport Differential Revision: [D76053764](https://our.internmc.facebook.com/intern/diff/D76053764/)
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 (oldest at bottom):
Improving the cpu implementation op_quantize to support input half dtype and adding additional testing
Differential Revision: D76053764