DQ→MatMulNBits fusion transformer for NvTensorRtRtx ep (#27466)
## Summary
Generalize the WebNN-specific DequantizeLinear → MatMulNBits graph
fusion transformer so it can be
reused by other execution providers (e.g. NvTensorRTRTX), and add
defensive shape/size validation
to prevent crashes on malformed tensors.
### Fusion patterns
**Pattern 1:** `DequantizeLinear → Reshape → Transpose → [Cast] →
MatMul/Gemm` → **MatMulNBits**
**Pattern 2:** `DequantizeLinear (axis=0) → MatMul/Gemm` →
**MatMulNBits**
---------
Co-authored-by: praneshgo <227579474+praneshgo@users.noreply.github.com>