yera.setup.model_discovery.llama_cpp

Discover model configuration from local GGUF files.

Symbols

class LlamaCppModelSetup — Discover local GGUF models from configured directories.

LlamaCppModelSetup

Discover local GGUF models from configured directories.

Discovery recursively scans each configured directory and reads GGUF metadata used to identify, classify, and describe supported models. It does not load model weights for inference or contact a remote service.

Scanning may take a while when the directories contain many GGUF files. Continuation shards are ignored, while inaccessible directories and unreadable files are reported as recoverable diagnostics. Discovery returns configuration and diagnostics without persisting them.

Methods

get_config — Obtain model configuration from local GGUF files.

LlamaCppModelSetup.get_config

get_config() → SetupResult[list[ModelConfig]]

Obtain model configuration from local GGUF files.

Configured directories are scanned recursively, which may take a while when they contain many GGUF files. Discovery reads model metadata but does not load model weights for inference. Continuation shards are ignored. Unreadable files and inaccessible directories are omitted with recoverable warnings rather than aborting the complete scan.

Returns

type: SetupResult[list[ModelConfig]]

Supported llama.cpp model configuration and discovery diagnostics. The result is not persisted by this operation.