[tests] add test for hotswapping + compilation on resolution changes #11825
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
|
Cc: @StrongerXi and @anijain2305 as well. |
sayakpaul
added
performance
sayakpaul
commented
Jun 28, 2025
| @@ -1350,7 +1350,6 @@ def test_model_parallelism(self): | |||
| new_model = self.model_class.from_pretrained(tmp_dir, device_map="auto", max_memory=max_memory) | |||
| # Making sure part of the model will actually end up offloaded | |||
| self.assertSetEqual(set(new_model.hf_device_map.values()), {0, 1}) | |||
| print(f" new_model.hf_device_map:{new_model.hf_device_map}") | |||
There was a problem hiding this comment.
Unrelated but hopefully okay :-)
sayakpaul
commented
Jun 28, 2025
tests/models/test_modeling_common.py
Outdated
Comment on lines
2121
to
2127
| if different_resolutions is not None: | ||
| for height, width in self.different_shapes_for_compilation: | ||
| new_inputs_dict = self.prepare_dummy_input(height=height, width=width) | ||
| _ = model(**new_inputs_dict) | ||
| else: | ||
| output0_after = model(**inputs_dict)["sample"] | ||
| assert torch.allclose(output0_before, output0_after, atol=tol, rtol=tol) |
There was a problem hiding this comment.
We don't need assertions when testing for different shapes as that would make the test unnecessarily complicated. We just check for recompilations.
sayakpaul
commented
Jun 28, 2025
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
BenjaminBossan
approved these changes
Jun 30, 2025
StrongerXi
reviewed
Jun 30, 2025
| @@ -315,6 +315,8 @@ pipeline.load_lora_weights( | |||
| > [!TIP] | |||
| > Move your code inside the `with torch._dynamo.config.patch(error_on_recompile=True)` context manager to detect if a model was recompiled. If a model is recompiled despite following all the steps above, please open an [issue](https://github.com/huggingface/diffusers/issues) with a reproducible example. | |||
| If you expect to varied resolutions during inference with this feature, then make sure set `dynamic=True` during compilation. Refer to [this document](../optimization/fp16#dynamic-shape-compilation) for more details. | |||
There was a problem hiding this comment.
I wonder if we should publicize use_duck_shape = False as well...
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.
What does this PR do?
As promised :)