onnxruntime
fix: skip DQ->MatMulNBits fusion when weight/scale initializer is shared
#28326
Open

fix: skip DQ->MatMulNBits fusion when weight/scale initializer is shared #28326

Rishi-Dave
Rishi-Dave fix: reject DQMatMulToMatMulNBits fusion when weight/scale initialize…
53bf4067
tianleiwu tianleiwu requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 8 days ago
tianleiwu tianleiwu removed review request from copilot-pull-request-reviewer copilot-pull-request-reviewer 8 days ago
tianleiwu tianleiwu requested a review from jambayk jambayk 8 days ago
tianleiwu tianleiwu requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 8 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-05-03
tianleiwu
tianleiwu commented on 2026-05-07
Rishi-Dave test: add Gemm sibling test for shared-weight guard; address review nits
dca3fee5
Rishi-Dave

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone