tts onnx gpu inference time problems

hi, i met a problem when onnx inference on gpu
1. onnx inference on gpu slower than onnx cpu inference much time and sometimes faster than gpu pt inference(2 times acceleration)
2. when i inference same text twice or more, inference achieves 2 time acceleration compare to gpu pt inference
any advicec?
thanks

Start by reproducing the reported GPU and CPU inference timings for the same text, including repeated inferences, and compare them with GPU PyTorch timings. The issue does not name a source file or test; done means identifying the cause of the inconsistent performance and documenting or validating a measurable improvement.

Written by the indexing model from the issue text.