[Parity with vLLM, SGLang, ATOM]: Public Nightly NGC docker images too

### 🚀 The feature, motivation and pitch AMD ATOM, vLLM (CUDA & AMD), SGLang (CUDA & AMD) all public nightly docker images. Can TRTLLM have public nightly ngc docker image builds too? https://hub.docker.com/r/rocm/atom-dev https://hub.docker.com/r/vllm/vllm-openai/tags https://hub.docker.com/r/vllm/vllm-openai-rocm/tags https://hub.docker.com/r/lmsysorg/sglang-rocm/tags https://hub.docker.com/r/lmsysorg/sglang/tags?page=2 +viz @xinli-sw @ncomly-nvidia @kedarpotdar-nv ### Alternatives _No response_ ### Additional context end user wastes couple hours building image by themselves ### Before submitting a new issue... - [x] Make sure you already searched for relevant issues, and checked the [documentation](https://nvidia.github.io/TensorRT-LLM/) and [examples](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples) for answers to frequently asked questions.