Remove preserve_zero and zero_point_domain from choose_qparams_affine #2149
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/2149
Note: Links to docs will display an error until the docs builds have been completed. ❌ 9 New FailuresAs of commit 414df66 with merge base 137b079 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jainapurva
added
topic: not user facing
jerryzh168
reviewed
Apr 30, 2025
jerryzh168
reviewed
Apr 30, 2025
jerryzh168
reviewed
Apr 30, 2025
| def choose_qparams_affine_tiny_gemm( | ||
| input: torch.Tensor, | ||
| mapping_type: MappingType, | ||
| block_size: Tuple[int, ...], |
There was a problem hiding this comment.
nit: change this to Tuple[int] as well to be consistent, assuming it means the same thing
There was a problem hiding this comment.
Block size is tuple with multiple integers, hence will need to do Tuple[int, ...]
jerryzh168
reviewed
Apr 30, 2025
Comment on lines
+780
to
+785
| target_dtype: torch.dtype, | ||
| quant_min: Optional[Union[int, float]] = None, | ||
| quant_max: Optional[Union[int, float]] = None, | ||
| eps: Optional[float] = None, | ||
| scale_dtype: Optional[torch.dtype] = None, | ||
| zero_point_dtype: Optional[torch.dtype] = None, |
There was a problem hiding this comment.
I think we could probably simplify this list as well, only configurable things are needed, this can be a separate PR
jerryzh168
reviewed
Apr 30, 2025
Comment on lines
+850
to
+855
| target_dtype: torch.dtype, | ||
| quant_min: Optional[Union[int, float, bool]] = None, | ||
| quant_max: Optional[Union[int, float, bool]] = None, | ||
| eps: Optional[float] = None, | ||
| scale_dtype: Optional[torch.dtype] = None, | ||
| zero_point_dtype: Optional[torch.dtype] = None, |
jerryzh168
reviewed
Apr 30, 2025
| MappingType.SYMMETRIC.name, | ||
| MappingType.SYMMETRIC_NO_CLIPPING_ERR.name, | ||
| MappingType.ASYMMETRIC.name, | ||
| MappingType.SYMMETRIC, |
There was a problem hiding this comment.
if this op has to be lowered, we'd need to use str instead of enum
There was a problem hiding this comment.
For all the new ops I've used MappingType enum. Should I update them to str?
jerryzh168
reviewed
May 1, 2025
| @@ -301,12 +305,6 @@ def quantize_affine( | |||
| output_dtype (torch.dtype): requested dtype (e.g. torch.uint8) for output Tensor | |||
| quant_min (Optional[int]): minimum quantized value for output Tensor, if not specified, it will be derived from dtype | |||
| quant_max (Optional[int]): maximum quantized value for output Tensor, if not specified, it will be derived from dtype | |||
| zero_point_domain (ZeroPointDomain): the domain that zero_point is in, should be either integer or float | |||
There was a problem hiding this comment.
we should probably preserve these for now, and move to quant_api, same for the doc for peserve_zero arg
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.
No description provided.