DQ→MatMulNBits fusion transformer for NvTensorRtRtx ep #27466
optimizer: fuse WebNN DQ chain back to MatMulNBits for NvTensorRTRTX
7e665906
optimizer(webnn): keep DQ->MatMulNBits fusion on phase-1 safe path
0434a1f4
optimizer(webnn): restore Gemm bias preserving DQ to MatMulNBits fusi…
e38ae4fa
Add SDXL Turbo fusion pattern for QDQ+MatMul -> MatMulNBits fusion
e4332496
optimizer(webnn): harden direct DQ->MatMulNBits fusion shape checks
887b6251
file name changes
f98418ff
refactor: split DQMatMulNBitsFusion::ApplyImpl into focused helpers
8559bcd8
anujj
force pushed
from
fbce2c02
to
210a7c41
10 days ago
anujj
force pushed
from
210a7c41
to
143f7e04
10 days ago
address PR review: config-driven gating, SafeInt, minimal-build guard…
40207a90
anujj
force pushed
from
143f7e04
to
40207a90
10 days ago
tianleiwu
approved these changes
on 2026-03-04
tianleiwu
enabled auto-merge (squash) 9 days ago
tianleiwu
merged
5c3f5449
into main 9 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub