API reference

lllm3090.config	Paths, ports and the hardware envelope this project targets.
lllm3090.hardware	Which GPU is in the machine, and what may be claimed for it.
lllm3090.storage	Which physical disk backs a path, and whether a faster one is going spare.
lllm3090.catalog	The curated model list, and the arithmetic that decides what fits.
lllm3090.gguf	Read what a GGUF says about itself, without loading it.
lllm3090.sweep	Survey what is published, and price it against the card in this machine.
lllm3090.engines	The llama.cpp build this project runs, and the ones it measures against.
lllm3090.speculation	What the engine is told to guess with, and which backend each setting wins on.
lllm3090.engine	Lifecycle for the llama.cpp server.
lllm3090.downloads	Background model downloads with real progress.
lllm3090.preflight	Checks that answer "will this machine run the stack" before it is asked to.
lllm3090.state	One description of the machine, in one shape, served by /api/status.
lllm3090.panel	The control panel: a loopback-only web UI for starting, stopping and downloading models.
lllm3090.cli	The lllm3090 command.