Use compile-time autotune for the Qwen3.5 CUDA export on PyTorch 2.14 - #23140

Use compile-time autotune for the Qwen3.5 CUDA export on PyTorch 2.14#23140

Gasoonjia merged 6 commits into

mainpytorch/executorch:mainfrom

gasoonjia/fix-qwen35-cuda-exportpytorch/executorch:gasoonjia/fix-qwen35-cuda-exportCopy head branch name to clipboard