support int8 scaled embedding bag pattern match #3463
Draft
+125
−32
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3463
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
Xia-Weiwen
approved these changes
Dec 15, 2025
| ) | ||
| return res | ||
|
|
||
| def _q(self, x): |
Collaborator
There was a problem hiding this comment.
Suggested change
| def _q(self, x): | |
| def _quantize(self, x): |
| def test_fp8_scaled_embedding_bag(self): | ||
| dtype = torch.float8_e4m3fn | ||
|
|
||
| def _test_scaled_embedding_bag_helper(self, dtype, with_quant=False): |
Collaborator
There was a problem hiding this comment.
Suggested change
| def _test_scaled_embedding_bag_helper(self, dtype, with_quant=False): | |
| def _test_scaled_embedding_bag_helper(self, dtype, with_output_quant=False): |
| counters["inductor"]["scaled_embedding_bag_matcher_nodes"] += len(match.nodes) | ||
| counter_name = "scaled_embedding_bag" | ||
| if "o_dtype" in kwargs: | ||
| counter_name += "_with_quant" |
Collaborator
There was a problem hiding this comment.
Suggested change
| counter_name += "_with_quant" | |
| counter_name += "_with_output_quant" |
| def matcher_check_fn(): | ||
| counter_name = "scaled_embedding_bag" | ||
| if with_quant: | ||
| counter_name += "_with_quant" |
Collaborator
There was a problem hiding this comment.
Suggested change
| counter_name += "_with_quant" | |
| counter_name += "_with_output_quant" |
| self.weight_scale = 2.0 | ||
| self.output_scale = 3.0 | ||
|
|
||
| def _dq(self, weight): |
Collaborator
There was a problem hiding this comment.
Suggested change
| def _dq(self, weight): | |
| def _dequantize(self, weight): |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Fuse dq + embeddingbag => _scaled_embedding_bag
Blocked by #3406