Is there a CLI command for llama-server to find out does the llama.cpp server run on Linux machine?

[morozover]

For example the CLI command for Nginx:
nginx -V

For Ollama:
ollama -v

I know that I can do this:
curl -i localhost:8080/health
But it isn't what I find

May be some llama-server -health command is available

[morozover]

Any suggestions?

[morozover]

Maybe anyone knows the answer?

[morozover]

Why don't these command work?

llama-server --version
.llama-server --version
./llama-server --version
llama-server -h
.llama-server -h
./llama-server -h

Output in CLI:
llama-server: command not found

While this works on the same server:
curl -i localhost:8080/health

[BradHutchings]

Are you looking for this?

ps axc | grep "llama-server"

[morozover]

@BradHutchings

Not at all
I'm searching for CLI command for llama-server tool

[YannFollet]

git clone https://github.com/ggml-org/llama.cpp.git
https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md

in llama.cpp folder after cmake (follow the instruction to build on your system)

build/bin/llama-server --version

ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
version: 6123 (79c1160b)
built with cc (Ubuntu 12.3.0-17ubuntu1) 12.3.0 for x86_64-linux-gnu

llama-server --help
...

ask an api end point information about the system where it is hosted looks like a vulnerability