Dang Bao Chien

I tried offline decoding using hlg_decode.cu and online decoding using online_decode.cu. And here is the result: - For model [librispeech conformer ctc](https://huggingface.co/csukuangfj/icefall-asr-librispeech-conformer-ctc-jit-bpe-500-2021-11-09/tree/main): offline decoding: 3.49% WER, online decoding: 19.08% WER...

Hi team, I would like to use the LogitsPostProcessor in the [C++ Executor API](https://github.com/NVIDIA/TensorRT-LLM/blob/main/cpp/include/tensorrt_llm/executor/executor.h) to control the generation of language models. However, unlike frameworks like Hugging Face, vLLM, or the...