when use engine optimum device tensorrt，startup fail

Nobody has claimed this yet.

### System Info

infinity_emb v2 --model_id /home/xxxx/peg_onnx --served-model-name embedding --engine optimum --device tensorrt --batch-size 32
OS: linux
model_base PEG
nvidia-smi: cuda version 11.8, tensorrt: 8.6.1

### Information

- [ ] Docker
- [X] The CLI directly via pip

### Tasks

- [x] An officially supported command
- [ ] My own modifications

### Reproduction

1、just startup

### Expected behavior

python3.10/dist-packages/optimum/onnxruntime/model_ort.py line 1444, in forward
model_outputs = self.__prepare_onnx_outputs(use_torch, **onnx_outputs)
python3.10/dist-packages/optimum/onnxruntime/modeling_ort.py line 939 in __prepare_onnx_outputs
model_outputs[output_name]=onnx_outputs[idx]
IndexError: tuple index out of range

then i print log with model run inputs and outputs , **find warmup model , first inference is ok , twice is error**
if i startup with --no-model-warmup, server can startup , but twice inference also error

Start by reproducing the documented `infinity_emb v2` command with `--engine optimum --device tensorrt`, then inspect the reported `optimum/onnxruntime/model_ort.py` and `modeling_ort.py` paths around output preparation. Compare the warmup, first-inference, and second-inference logs; done means repeated inference succeeds without requiring `--no-model-warmup`.

Written by the indexing model from the issue text.