Fix: Resolve #3060, preload_module_classes is lost for nested modules
#3248
Conversation
This file contains 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
4 tasks
SunMarc
approved these changes
Nov 22, 2024
|
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. |
muellerzr
reviewed
Nov 22, 2024
wejoncy
changed the title
wejoncy
changed the title
wejoncy
changed the title
preload_module_classes is lost for nested modules
|
Hi @muellerzr and @SunMarc Thanks for your review. I have briefly described the issue in overview of this PR. |
SunMarc
reviewed
Nov 26, 2024
SunMarc
reviewed
Nov 26, 2024
| @@ -762,3 +762,64 @@ def test_save_model_with_stateful_dataloader(self, use_safetensors, tied_weights | |||
| assert torch.allclose(original_linear1, new_linear1) | |||
| assert torch.allclose(original_batchnorm, new_batchnorm) | |||
| assert torch.allclose(original_linear2, new_linear2) | |||
|
|
|||
| @require_cuda | |||
There was a problem hiding this comment.
we need a require_transformers decorator if you are going to import transformers here. Otherwise, we can try to not use it and just save the model with
checkpoint = os.path.join(tmp_dir, "pt_model.bin")
torch.save(model.state_dict(), checkpoint)
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Outdated suggestions cannot be applied.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?
We ran into this issue when try to load VPTQ models by multiple devices, the
VQLinearlayer has embending as its sub-module. This function should move all constant buffers/parameters to the corresponding devices from Meta device.So
add_hook_to_moduleshould passpreload_module_classesto the next recursive calling for the nested modules.https://github.com/microsoft/VPTQ/blob/ac7258f461e214ca705f5895513f314576750528/vptq/layers/vqlinear.py#L160C18-L160C18
This PR is to fix #3060