Add SplitTensorsTransform to QEFFAutoModel to prevent >2GB protobuf export issue#950
Open
quic-rishinr wants to merge 1 commit intoquic:mainfrom
Open
Add SplitTensorsTransform to QEFFAutoModel to prevent >2GB protobuf export issue#950quic-rishinr wants to merge 1 commit intoquic:mainfrom
quic-rishinr wants to merge 1 commit intoquic:mainfrom
Conversation
…xports Signed-off-by: Rishin Raj <rishinr@qti.qualcomm.com>
Contributor
Author
|
CI-Ready |
vbaddi
requested changes
Apr 30, 2026
Contributor
vbaddi
left a comment
vbaddi
left a comment
There was a problem hiding this comment.
@quic-rishinr as discussed, lets disable the split transform and fix the onnx.save thing. thanks
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add SplitTensorsTransform to QEFFAutoModel to prevent >2GB protobuf exports
FP16ClipTransform inlines external weights, causing large embedding
models (e.g. BAAI/bge-reranker-v2-m3) to exceed the 2GB ModelProto
parser limit in the AIC compiler
Adding SplitTensorsTransform to _onnx_transforms spills large
initializers to sidecar *.onnx.data files. Updated existing tests
and added regression tests to verify external data spilling behavior.