Skip to content

[Quant][PT2E][X86] Enable annotation of aten.mul.tensor with X86InductorQuantizer#2075

Merged
Xia-Weiwen merged 1 commit into
pytorch:mainfrom
Xia-Weiwen:annotate_mul_tensor
Apr 24, 2025
Merged

[Quant][PT2E][X86] Enable annotation of aten.mul.tensor with X86InductorQuantizer#2075
Xia-Weiwen merged 1 commit into
pytorch:mainfrom
Xia-Weiwen:annotate_mul_tensor

Conversation

@Xia-Weiwen

@Xia-Weiwen Xia-Weiwen commented Apr 18, 2025 •
edited
Loading

Copy link
Copy Markdown
Collaborator

Summary
(It's a port from pytorch/pytorch#150831)
This PR enabled annotation of aten.mul.tensor with X86InductorQuantizer. However, mul is not annotated by default. Users need to set the following to enable annotation of mul:

quantizer.set_function_type_qconfig(
    torch.mul, quantizer.get_global_quantization_config()
)

After convert_pt2e, users get patterns like

quantize_per_tensor_default = torch.ops.quantized_decomposed.quantize_per_tensor.default(x, ...)
dequantize_per_tensor_default = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default, ...)
quantize_per_tensor_default_1 = torch.ops.quantized_decomposed.quantize_per_tensor.default(y, ...);
dequantize_per_tensor_default_1 = torch.ops.quantized_decomposed.dequantize_per_tensor.default(quantize_per_tensor_default_1, ...)
mul = torch.ops.aten.mul.Tensor(dequantize_per_tensor_default, dequantize_per_tensor_default_1);

Test plan

pytest test/quantization/pt2e/test_x86inductor_quantizer.py -k test_annotate_mul_tensor

@pytorch-bot

pytorch-bot Bot commented Apr 18, 2025 •
edited
Loading

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2075

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit f01c1fa with merge base 34421b1 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 18, 2025
@Xia-Weiwen Xia-Weiwen added the topic: new feature Use this tag if this PR adds a new feature label Apr 18, 2025
leslie-fang-intel
leslie-fang-intel approved these changes Apr 18, 2025
View reviewed changes

@leslie-fang-intel leslie-fang-intel left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@Xia-Weiwen Xia-Weiwen requested a review from jerryzh168 April 21, 2025 01:58
@Xia-Weiwen

Xia-Weiwen commented Apr 22, 2025

Copy link
Copy Markdown
Collaborator Author

Hi @jerryzh168 Could you please review this PR? Thanks.

@Xia-Weiwen Xia-Weiwen marked this pull request as ready for review April 23, 2025 06:10
@Xia-Weiwen Xia-Weiwen merged commit ddce558 into pytorch:main Apr 24, 2025
liangel-02 pushed a commit that referenced this pull request Aug 25, 2025
@Xia-Weiwen @liangel-02
[Quant][PT2E][X86] Enable annotation of aten.mul.tensor with X86Induc…
466464b 
…torQuantizer (#2075)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@jerryzh168 jerryzh168 jerryzh168 approved these changes

@leslie-fang-intel leslie-fang-intel leslie-fang-intel approved these changes

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: new feature Use this tag if this PR adds a new feature

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@Xia-Weiwen @jerryzh168 @leslie-fang-intel @facebook-github-bot