[quant] Add saturate_to_fp16 op for FP16 quant support #42147
Closed
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
Summary: Op to check the range of a tensor and clamp the values to fp16 range This operator will be inserted into the graph in subsequent diffs. Test Plan: python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Jul 28, 2020
Summary: Op to check the range of a tensor and clamp the values to fp16 range This operator will be inserted into the graph in subsequent diffs. Test Plan: python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 25a5314 Pull Request resolved: #42147
💊 CI failures summary and remediationsAs of commit 2535659 (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions on the GitHub issue tracker or post in the (internal) Dr. CI Users group. This comment has been revised 8 times. |
This was referenced Jul 29, 2020
vkuzo
approved these changes
Jul 29, 2020
| } | ||
|
|
||
| template <typename T> | ||
| bool CheckAndSaturate(T max_val, T* element) { |
Contributor
There was a problem hiding this comment.
optional: I realize this is just moving code around, but this API seems to require careful reading to understand it correctly. Might be worth a refactor in the future to make it a void return type, and have the status be a var passed by reference.
Summary: Op to check the range of a tensor and clamp the values to fp16 range This operator will be inserted into the graph in subsequent diffs. Test Plan: python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
Summary: Op to check the range of a tensor and clamp the values to fp16 range This operator will be inserted into the graph in subsequent diffs. Test Plan: python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
Summary: Op to check the range of a tensor and clamp the values to fp16 range This operator will be inserted into the graph in subsequent diffs. Test Plan: python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D22849221](https://our.internmc.facebook.com/intern/diff/D22849221) [ghstack-poisoned]
Contributor
|
This pull request has been merged in a9eebaf. |
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:
Op to check the range of a tensor and clamp the values to fp16 range
This operator will be inserted into the graph in subsequent diffs.
Test Plan:
python test/test_quantization.py TestQuantizedTensor.test_fp16_saturate_op
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D22849221