fix: skip DQ->MatMulNBits fusion when weight/scale initializer is shared #28326
fix: reject DQMatMulToMatMulNBits fusion when weight/scale initialize…
53bf4067
test: add Gemm sibling test for shared-weight guard; address review nits
dca3fee5
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub