[WebGPU] Fuse rank-32 quantized LoRA with MatMulNBits - #33370

[WebGPU] Fuse rank-32 quantized LoRA with MatMulNBits#33370

Jiajia Qin (qjia7) wants to merge 44 commits into

microsoft:mainmicrosoft/onnxruntime:mainfrom

qjia7:feat/webgpu-matmul-nbits-qloraqjia7/onnxruntime:feat/webgpu-matmul-nbits-qloraCopy head branch name to clipboard