modify unflatten for vllm #3297
Open
+36
−5
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/3297
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit cdc5ca2 with merge base 6c78c4d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
liangel-02
added
the
topic: improvement
liangel-02
force-pushed
the
update_metadata_structure
branch
5 times, most recently
from
1788f28 to
0e290bb
Compare
liangel-02
force-pushed
the
update_metadata_structure
branch
from
0e290bb to
cdc5ca2
Compare
jerryzh168
reviewed
Nov 13, 2025
| def unflatten_tensor_state_dict( | ||
| tensors_data_dict: Dict[str, Any], | ||
| metadata: Dict[str, Any], | ||
| is_last_file: bool = False, |
Contributor
There was a problem hiding this comment.
this seems hacky, why not just return the tensor names that's incomplete back to user?
jerryzh168
reviewed
Nov 13, 2025
| raise ValueError(f"Unsupported tensor type: {tensor_type}") | ||
|
|
||
| for tensor_name in to_be_deleted: | ||
| del tensors_data_dict[tensor_name] |
Contributor
There was a problem hiding this comment.
it's not a good practice to modify input, is it necessary?
jerryzh168
reviewed
Nov 13, 2025
Contributor
jerryzh168
left a comment
jerryzh168
left a comment
There was a problem hiding this comment.
I think current impl is a bit hacky, what we can do is:
unflatten_tensor_state_dict with incomplete state_dict:
return a tuple of (unflattened_state_dict, unused part of incomplete_state_dict)
next call: combine the new state_dict input, with the previous unconsumed part
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.
Summary
We keep track of what has been processed by deleting processed keys from the original state dict. This is for the case when not all tensor attributes are available to us when loading, so we reconstruct the tensor subclasses with missing attributes in a later call.
We expect the state dict to be empty after loading is complete
Test
python test/prototype/safetensors/test_safetensors_support.py