Bug: Server not support mmproj

[lld1995]

What happened?

I use Yi-VL-6B,and i run it with ./server -m /data/model_data/Yi-VL-6B-GGUF/ggml-model-f16.gguf --n-gpu-layers 4096 -n 384 -c 2048 --host 0.0.0.0 --port 8897 --mmproj /data/model_data/Yi-VL-6B-GGUF/mmproj-model-f16.gguf

But when i upload image on web, it shows

Name and Version

/data/llama.cpp/build/bin$ ./server --version
version: 3137 (dcf7527)
built with cc (Ubuntu 10.5.0-1ubuntu1~20.04) 10.5.0 for x86_64-linux-gnu

What operating system are you seeing the problem on?

No response

Relevant log output

No response

[ngxson]

For now, server does not support vision model

Edit: related to #8010

[lld1995]

https://github.com/trzy/llava-cpp-server

The project is reliable? It has some unpredictable issue?

[ngxson]

@lld1995 The mentioned project is not maintained by llama.cpp, so I cannot answer your question.