Crate blazen_model_cache 

Shared model download and cache layer for Blazen local-inference backends.

Provides ModelCache for downloading and caching ML models from HuggingFace Hub. Designed to be shared by all local-inference backends (fastembed, mistral.rs, whisper.cpp, etc.).

wasm32 support

On wasm32-* targets the underlying download stack (hf-hub, dirs, tokio::fs) is not available, so ModelCache is a stub that always returns CacheError::Unsupported. Browser/Worker callers should obtain model bytes through a different mechanism (e.g. fetch() on the JS side, pre-bundled assets, or a manually populated cache directory).

Structs

ModelCache

Local cache for ML models downloaded from HuggingFace Hub.

Enums

CacheError

Errors that can occur during model cache operations.

Traits

ProgressCallback

Callback trait for receiving download progress updates.