NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE. (error_code: 1)

[jeevanmac011769]

Describe the issue

Issue: I am encountering this error when i launch my model and run it in the gradio. NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE. (error_code: 1) please help me.

Screenshots: I have attached the screenshots here

[jiuge4010]

I am encountering this error,please are you solve this problem?

[samueleruffino99]

I am having the same issue for now

[foundwant]

same error! the latest code should have bugs, step by the readme, will meet this bug always.

[caixiaoniweimar]

same

[seasoncool]

same +1

[Z500-RAY]

same +1

[LivioGama]

I have the same error. Gonna try to dig. Does anyone know if older versions were working?

[LivioGama]

Alright guys, after investigating a bit, I think I understood the problem. Although the error message is not very clear, it simply look like you cannot run and have the workers working on a VPS without GPU. I was assuming that GPU was a plus and it would run on the rest in "best effort" mode, but it's unlikely.... The error message was laying there since the beginning :/ and I thought it was a warning.

[shirley-wu]

Hi, for me the problem is resolved by running gradio demo AFTER the backend is setup, rather than in the second step right after controller is launched as in README. So my actually order would be

python -m llava.serve.controller --host 0.0.0.0 --port 10000
CUDA_VISIBLE_DEVICES=0,1 python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.6-34b --tokenizer-path liuhaotian/llava-v1.6-34b-tokenizer --port 30000 --tp 2
python -m llava.serve.sglang_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --sgl-endpoint http://127.0.0.1:30000
python -m llava.serve.gradio_web_server --controller http://localhost:10000 --model-list-mode reload --share