Deleted model after export to save memory #521
+245
−11
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
asmigosw
requested review from
quic-rishinr,
ochougul,
quic-hemagnih and
quic-amitraj
as code owners
asmigosw
force-pushed
the
memory_reduction
branch
from
3e2d96b to
8bca803
Compare
ochougul
reviewed
Aug 14, 2025
QEfficient/base/modeling_qeff.py
Outdated
| # self.state_dict = self.model.state_dict() | ||
|
|
||
| # Loading model if weights are in meta state from state_dict | ||
| if any(name for name, param in self.model.named_parameters() if param.is_meta): |
There was a problem hiding this comment.
can't we do this check without the for loop, this will loop over all the model params, we can check only one right?
or add a attribute to a model. and check based on that.
There was a problem hiding this comment.
I have added a variable and added an or condition in the latest code
ochougul
requested changes
Aug 14, 2025
quic-rishinr
force-pushed
the
memory_reduction
branch
from
a1550f8 to
0bce273
Compare
quic-hemagnih
approved these changes
Aug 19, 2025
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
… better to clean the model before applying onnx transform and code clean up Signed-off-by: Rishin Raj <[email protected]>
Signed-off-by: Rishin Raj <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
asmigosw
force-pushed
the
memory_reduction
branch
from
c944a59 to
0fafed6
Compare
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
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Outdated suggestions cannot be applied.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.
Deleting the model after export is complete and storing only necessary params required either at compile or generation.