support for tensorrtllm_backend input template

[Alireza3242]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

I want to add my tensorrt llm model that is served in tritonserver.
But in tensorrt llm backend project the input template is diferent with the triton that dify supports. you can see it in:
https://github.com/triton-inference-server/tensorrtllm_backend/blob/main/all_models/inflight_batcher_llm/ensemble/config.pbtxt

can you add this template?

2. Additional context or comments

tensorrtllm_backend is officially supported by nvidia. If you add thier template, it will help us.

3. Can you help us with this feature?

• I am interested in contributing to this feature.

[crazywoola]

Please checkout the new version https://github.com/langgenius/dify/releases/tag/1.0.0-beta.1, if you have new model providers or tools that you want to contribute.
#11588