[quant][pyper] Set sparse to False for embedding_bag ops in graph mode #45997
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: The current sparse field using in the float module is for sparse gradients, which is not applicable to inference. The sparse field in the quantizd ops denotes pruned weights. Test Plan: python test/test_quantization.py TestQuantizeDynamicJitOps.test_embedding_bag Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Oct 7, 2020
Summary: The current sparse field using in the float module is for sparse gradients, which is not applicable to inference. The sparse field in the quantizd ops denotes pruned weights. Test Plan: python test/test_quantization.py TestQuantizeDynamicJitOps.test_embedding_bag Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 221161b Pull Request resolved: #45997
facebook-github-bot
added
the
oncall: jit
supriyar
changed the title
…n graph mode" Summary: The current sparse field using in the float module is for sparse gradients, which is not applicable to inference. The sparse field in the quantizd ops denotes pruned weights. Test Plan: python test/test_quantization.py TestQuantizeDynamicJitOps.test_embedding_bag Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D24176543](https://our.internmc.facebook.com/intern/diff/D24176543) [ghstack-poisoned]
Codecov Report
@@ Coverage Diff @@
## gh/supriyar/195/base #45997 +/- ##
=====================================================
Coverage 68.28% 68.28%
=====================================================
Files 410 410
Lines 53306 53306
=====================================================
Hits 36398 36398
Misses 16908 16908 Continue to review full report at Codecov.
|
…n graph mode" Summary: The current sparse field using in the float module is for sparse gradients, which is not applicable to inference. The sparse field in the quantizd ops denotes pruned weights. Test Plan: python test/test_quantization.py TestQuantizeDynamicJitOps.test_embedding_bag Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D24176543](https://our.internmc.facebook.com/intern/diff/D24176543) [ghstack-poisoned]
vkuzo
approved these changes
Oct 8, 2020
| for (auto i = 1; i < inputs_size - 1; ++i) { | ||
| qembedding_bag_inputs.push_back(embedding_bag_inputs[i]); | ||
| } | ||
| // Set the sparse field to 0 for inference. |
There was a problem hiding this comment.
optional: should we mention that this is for sparse gradients (as the pr summary reads), just to make it clear on why?
…n graph mode" Summary: The current sparse field using in the float module is for sparse gradients, which is not applicable to inference. The sparse field in the quantizd ops denotes pruned weights. Test Plan: python test/test_quantization.py TestQuantizeDynamicJitOps.test_embedding_bag Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D24176543](https://our.internmc.facebook.com/intern/diff/D24176543) [ghstack-poisoned]
|
This pull request has been merged in 8c80ee8. |
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:
The current sparse field using in the float module is for sparse gradients, which is not applicable
to inference. The sparse field in the quantizd ops denotes pruned weights.
Test Plan:
python test/test_quantization.py TestQuantizeDynamicJitOps.test_embedding_bag
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D24176543