Crate zsfm_gguf 

Macros

tensor_map

Table-driven exact match with a fallback closure for prefix/layer rules.

Structs

GGUFFile

GGUFTensorInfo

GGUFWriter

Streaming GGUF v3 writer.

Enums

GGMLType

GGML tensor data types used in GGUF files. Values match the ggml_type enum in ggml.h.

GGUFMetaValue

A typed metadata value for a GGUF key-value pair.

GGUFValueType

GGUF metadata value types (gguf_metadata_value_type).

Constants

MAX_KV_COUNT

Hard caps so a corrupt header cannot trigger huge allocations.

MAX_N_DIMS

MAX_STRING_LEN

MAX_TENSOR_BYTES

MAX_TENSOR_COUNT

READ_BUF_CAPACITY

Capacity every model crate should wrap its BufReader<File> with before parsing a GGUF file. Header/metadata parsing is hundreds to thousands of few-byte read_u32/read_u64 calls (one per tensor dim, name length, metadata value, …); the default 8 KiB BufReader capacity is fine for small files but forces a syscall every few tensors on models with hundreds of them. 1 MiB comfortably covers any GGUF header in one underlying read while staying small relative to the model file itself.

Functions

map_with_table

Exact-match helper for tensor_map.rs files.