[LLM-8850] Is there something wrong in axcl_demo with depth-Anything ?

[phillipsback]

First , I wanna thanks group for update llm_model_qwen3-1.7B yesterday. It's very powerfull product, and I learn lots from it (eg: of course, with your website instruction).

I wanna check that, when I work with DepthAnything demo, couldn't get the result like website show.

Could you check that demo again, and kindly provide the way that I can get the right output.

Thanks.

[kuriko]

@phillipsback
Hi! Could you please provide us your result for us to check?

[phillipsback]

Of course. Log seems normal, but output pic kind of odd....
[My case]( image url)

[phillipsback]

There something interesting.

1. DepthAnything can be done with THIS

2. In OpenAI API, I think Mr. uzuki_aoba already post in Qiita. In the CMD that renew the model list got some TYPO "sudo systemctrl restart llm-openai-api"

3. I try LLM(qwen3), Whisper(CN), MeloTTS(CN), VLM(InternVL), they are work great with StackFlow that I can call by another computer in my house. But I think it something funny when I install llm-model-internVL. In apt I called is internvl____axcl, but after install the folder name came to internvl____AX650. (In the end, I change the folder name manually...)