onnxruntime
Add QDQFloatActivationsTransformer to remove activation Q→DQ pairs and enable MatMulNBits fusion
#27636
Open
Overview
Commits
5
Changes
View On GitHub

Add QDQFloatActivationsTransformer to remove activation Q→DQ pairs and enable MatMulNBits fusion #27636

jambayk wants to merge 5 commits into main from jambayk/qdq-opt
jambayk
jambayk jambayk requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 1 day ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-03-12
jambayk jambayk requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 1 day ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-03-12
jambayk jambayk force pushed from 4e937c9d to e827aa17 18 hours ago
jambayk jambayk force pushed from e827aa17 to 903db7dd 14 hours ago
jambayk init
b778a676
jambayk constant folding on DQ weights
52c1355c
jambayk address reviews
649a7f35
jambayk remove references to dqcastmatmul
fc8df15a
jambayk resolve graph
52bf578d
jambayk jambayk force pushed from 1d353913 to 52bf578d 7 hours ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum