Deleted model after export to save memory #521
Merged
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
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
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Outdated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): |
Contributor
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.
Contributor
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
Contributor
ochougul
left a comment
ochougul
left a comment
There was a problem hiding this comment.
Changes look good to me as first PR.
The re-loading part needs to be figured out, are you planning to do this in next PR?
Please clean the code, we are good to go.
quic-rishinr
force-pushed
the
memory_reduction
branch
from
a1550f8 to
0bce273
Compare
quic-hemagnih
approved these changes
Aug 19, 2025
Contributor
quic-hemagnih
left a comment
quic-hemagnih
left a comment
There was a problem hiding this comment.
Looks good to me, please run the CI. We can merge this now.
Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com>
Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com>
… better to clean the model before applying onnx transform and code clean up Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com>
asmigosw
force-pushed
the
memory_reduction
branch
from
c944a59 to
0fafed6
Compare
Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com>
Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com>
Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com>
ochougul
pushed a commit
that referenced
this pull request
Nov 3, 2025
Deleting the model after export is complete and storing only necessary params required either at compile or generation. --------- Signed-off-by: Asmita Goswami <asmigosw@qti.qualcomm.com> Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com> Co-authored-by: Rishin Raj <rishinr@qti.qualcomm.com> Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.