Crate combs_formats 

combs-formats

File-format adapter layer. The runtime and model crates never touch file formats directly; they go through the ModelSource trait (the LiteRT-LM ModelResources equivalent). Phase 1 ships the [safetensors] adapter (HuggingFace config.json + model.safetensors, mmap-backed, zero-copy views). GGUF / ONNX / litertlm adapters plug in here later by implementing the same trait.

Structs

GgufSource

A parsed GGUF file.

ModelMetadata

Architecture + hyperparameter description of a model, format-agnostic.

SafetensorsSource

ModelSource over a HuggingFace-format directory:

SamplerConfig

Default sampler parameters, typically from generation_config.json.

TensorReader

A lazy view over one tensor’s raw bytes inside a ModelSource.

TokenizerSpec

Where to find the tokenizer and which special tokens it defines.

VisionConfig

Vision-encoder hyperparameters parsed from config.json::vision_config (plus top-level scale_factor / image_token_id).

Enums

FormatError

Errors produced by format adapters.

TensorDtype

Element dtypes supported by the loaders.

Traits

ModelSource

The central adapter trait: a source of model weights + config, independent of the on-disk format (LiteRT-LM ModelResources equivalent).

Functions

open_model_source

Opens any supported model path: a .gguf file, or a directory in the HuggingFace safetensors layout. This is the single entry point the CLI, FFI and server use — format detection lives here.

Type Aliases

Result

Convenient result alias for this crate.