personal llm monitor tool to keep tabs on loaded models and their drain on system resources
Commit
f9d9792
I'm not sure whether to ask for a GH link or your prompt to self-build it these days.
commit f9d9792
no clue what prompt started this, but most likely some sort of iteration "help me replicate omlx's server health stats in a tui app".
if you want to save your tokens, here's a link: https://github.com/slogsdon/llm-monitor
GitHubGitHub - slogsdon/llm-monitor: Terminal dashboard and JSON reports for a local LLM stack on macOS: LiteLLM, llama-swap, oMLX/mlx_lm, OllamaTerminal dashboard and JSON reports for a local LLM stack on macOS: LiteLLM, llama-swap, oMLX/mlx_lm, Ollama - slogsdon/llm-monitor