Fix GatherBlockQuantized node to support symmetric quantized LM_HEAD#1951
Merged
Merged
Conversation
Today models created with python -m onnxruntime_genai.models.builder -p int4 -e webgpu --extra_options shared_embeddings=true int4_algo_config=rtn_last int4_is_symmetric=true have invalid GatherBlockQuanntized nodes because the zero point attribute of the node points to a non-existent tensor lm_head.MatMul.weight_zp. This change fixes builder.py, so that we are selective about adding that attribute to the GatherBlockQuantized node.
kunal-vaishnavi
approved these changes
Jan 22, 2026
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Today models created with
python -m onnxruntime_genai.models.builder -p int4 -e webgpu --extra_options shared_embeddings=true int4_algo_config=rtn_last int4_is_symmetric=true
have invalid GatherBlockQuanntized nodes because the zero point attribute of the node points to a non-existent tensor lm_head.MatMul.weight_zp.
This change fixes builder.py, so that we are selective about adding that attribute to the GatherBlockQuantized node.