Failed to build TensorRT-LLM backend for Triton server.

[sdecoder]

Greetings, I have come across following issue when trying to build TensorRT-LLM backend for Triton server:
/home/nvidia/projects/triton-inference-server/tensorrtllm_backend/inflight_batcher_llm/../tensorrt_llm/cpp/include/tensorrt_llm/common/dataType.h:40:30: error: ‘kFP4’ is not a member of ‘nvinfer1::DataType’; did you mean ‘kFP8’?

I followed the instruction found here:
https://github.com/triton-inference-server/tensorrtllm_backend/blob/main/docs/build.md
1.1. The command I am using is:
/home/nvidia/projects/triton-inference-server/tensorrtllm_backend/inflight_batcher_llm
bash scripts/build.sh
1.2. Platform: Jetson AGX Orin;
1.3. TensorRT version: TensorRT-10.3.0.26
1.4. CUDA version: 12.6
I do believe the TensorRT version and CUDA version is compatible.
Is anyone will to take a look at this and give me a hint?
Thank you everyone.

[dog-dev-mel]

I guess TensorRT-LLM backend is not avaliable on Jetson Device.