fix: improve weight offloading to handle plain tensor attrs and use to_empty()#952
Open
quic-rishinr wants to merge 1 commit intoquic:mainfrom
Open
fix: improve weight offloading to handle plain tensor attrs and use to_empty()#952quic-rishinr wants to merge 1 commit intoquic:mainfrom
quic-rishinr wants to merge 1 commit intoquic:mainfrom
Conversation
…o_empty() Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
quic-rishinr
force-pushed
the
mem_optim_v2
branch
from
67e71d9 to
31ee8a3
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
fix: improve weight offloading to handle plain tensor attrs and use to_empty()
Replace manual storage resizing with
to_empty(device="meta")forparameters/buffers and explicitly handle plain tensor attributes (e.g.
stacked expert weights in MoE models) that are not registered as
parameters or buffers. This ensures all tensors are properly moved to
the meta device, reducing memory usage after ONNX export.
Add unit tests for plain tensor attribute clearing