onnxruntime
81a04ca4 - [webgpu] Fix the wrong fallback in Attention (#26608)

Commit
75 days ago
[webgpu] Fix the wrong fallback in Attention (#26608) Attention input handling updates: * Corrected the input indices for `past` from `input[5]` to `input[4]` in the fallback logic, ensuring the code reflects the actual input order. With this change, the Attention ops in phi-4-mm-vision.onnx can go to the gpu instead of cpu.
Author
Parents
Loading