Sangchun Ha

# 🚀 Add huggingface tokenizer  tokenizers : [https://github.com/huggingface/tokenizers](https://github.com/huggingface/tokenizers) ## Motivation - We can tokenize easily and quickly using tokenizers. - We can easily apply various tokenizers. ## Your contribution...

Is there an easy way to set model max length to 10 or 20 seconds?

2

Thank you so much for sharing the amazing repo. I have a question, so I'm leaving an issue. I'm currently using the model by directly loading it without using a...

tensorrtllm and vllm backend results are different using genai-perf

1

Thank you for releasing a great project. I measured [`genai-perf`](https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/perf_analyzer/genai-perf/docs/tutorial.html#profile-gpt2-running-on-triton-tensorrt-llm) by running the [rtzr/ko-gemma-2-9b-it](https://huggingface.co/rtzr/ko-gemma-2-9b-it) (gemma-2-9b-it fine-tuning model) model with the `tritonserver vllm backend` and `tritonserver tensorrt_llm backend`. However, the two...

[Bug] Why can't I use multi-lora adapter and radix attention together?

2

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...

## ✨ Description When using metis, an error occurs saying that langid cannot be imported. I fix `langid` to `py3langid as langid`. https://github.com/open-mmlab/Amphion/blob/main/models/tts/metis/metis.py#L21 ## 🚧 Related Issues [List the issue...