Harry

> 你好，可以根据这个 [README](https://huggingface.co/openbmb/MiniCPM-o-2_6-int4#usage-of-minicpm-o-2_6-int4) 步骤安装 `AutoGPTQ` 使用 int4 量化推理 You can follow the steps in this [README](https://huggingface.co/openbmb/MiniCPM-o-2_6-int4#usage-of-minicpm-o-2_6-int4) to install `AutoGPTQ` and perform int4 quantized inference. It can NOT work, after installation...

Hello, @alastorid I'm source melo TTS recently, and try implement this model to edge devcie. Follow your PR, I meet below problem. Please have a time to help, thank you!...

@alastorid, Thank you for your quick response, new PR is works well. I have tried two kinds of development platform, the PR both are effective.

@AnyaCoder Hello, first of all, let me thank you for your support. I meet the same issue (AttributeError: 'Qwen2TokenizerFast' object has no attribute 'semantic_id_to_token_id'), when run agent-v0.1-3b, based on speech-1.5....

> > @AnyaCoder Hello, first of all, let me thank you for your support. I meet the same issue (AttributeError: 'Qwen2TokenizerFast' object has no attribute 'semantic_id_to_token_id'), when run agent-v0.1-3b, based...

After upgrade gradio(4.26.0) to 4.44.1 by command(pip install gradio --upgrade, based on conda/python3.9/aarch64). Ignore below Error: "botocore 1.36.2 requires urllib3=1.25.4; python_version < "3.10", but you have urllib3 2.3.0 which is...

Copy PR to local code, it's works. Computing base on XPU(iGPU of Intel Ultra 7 155H). By the way, general GPU loading is around 30%. If there is has optimization...

Hi, @yukiarimo, Thank you for your quick response. I deploy Melo TTS on edge device, and the RTF reach to ~2.0, under Chinese(mix English) condition. That is great. Besides, I...

Follow below command, I can run Melo TTS server in RK3588(arm v8)+Ubuntu22.04. This is one key step: upgrade gradio after install dependencies, based on requirements. conda create -n melotts python=3.9...

I have no idea about this issue, I can't duplicate your issue on my local EVB.