Default to using edge_program state dict if quantization data not available#17452
Default to using edge_program state dict if quantization data not available#17452JakeStevens wants to merge 1 commit intopytorch:mainfrom
Conversation
…ilable Summary: PR pytorch#16901 added logic to replace FakeTensors with actually quantization data. The docstring says: ``` :param post_quantization_state_dict: State-dict of the model right after quantization. During partitioning, the `edge_program` only contains fake tensors without any data. In this case, this state dict is used instead (if provided). Notice: It may potentially contain outdated data, ``` with the key part being **if provided**. However, this is not the actual functionality. By not falling back, this introduces a regression for depthwise convolutions, which have a "no dynamic" constraint that is triggered by this missing information. This PR restores the original behavior if quantization data is not provided. Differential Revision: D93253828
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17452
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 1 Cancelled JobAs of commit 34e7a93 with merge base c12dc35 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D93253828. |
This PR needs a
|
Summary:
PR #16901 added logic to replace FakeTensors with actually quantization data.
The docstring says:
with the key part being if provided. However, this is not the actual functionality.
By not falling back, this introduces a regression for depthwise convolutions, which have a "no dynamic" constraint that is triggered by this missing information.
This PR restores the original behavior if quantization data is not provided.
Differential Revision: D93253828
cc @robert-kalmar @digantdesai