Module weights 

Weight loading from safetensors files (SBIO IORouter for filesystem I/O).

Modules

adapter

Split a tensor name into (everything but its last numeric path segment, that segment as a number) so names sort NUMERICALLY on the index. embedders.2 must precede embedders.10; a plain lexicographic sort puts 10 first and silently mis-maps every table after the ninth. PEFT adapter loader: adapter_model.safetensors → WeightStore.

mlx_int8

MLX uint32-packed 8-bit weight format support.

Structs

DeferredTensor

Where a skipped tensor lives, so a consumer can read it in place.

GgufLoader

Loads weights from a GGUF file, dequantizing every tensor to BF16 on the GPU.

SafetensorsLoader

Loads weights from safetensors files using mmap.

WeightStore

All model weights loaded onto the GPU, keyed by HuggingFace name.

WeightTensor

A weight tensor on the GPU.

Enums

WeightDtype

Data type of a weight tensor.

Traits

WeightLoader

SBIO IORouter trait for weight loading.

Functions

auto_detect_weight_prefix

Resolve the weight-key prefix a nested (multimodal) checkpoint uses.

config_from_gguf_dir

Build a ModelConfig from the .gguf in model_dir, with no config.json.

find_gguf

Locate the backbone GGUF weight file in dir. Returns the lexicographically-first non-mmproj *.gguf (also the first shard, *-00001-of-*, of a split file). The mmproj vision sidecar is excluded here and loaded separately (see sidecar::find_mmproj); a dir that is only an mmproj falls back to the first file so the caller still gets a path to error on.

is_ngram_table

Whether a tensor is an n-gram embedding TABLE — the huge blobs that are served off NVMe instead of being uploaded with the rest of the checkpoint.

parse_expert_index

Parse expert index from tensor name (e.g. “model.layers.3.mlp.experts.42.gate_proj.weight” → 42).