Module gguf_sharder 

Q-GGUF Hybrid Packaging Parses monolithic .gguf files: vocabulary (KV section) and tensor names/offsets (tensor-info section) are extracted into native Rust types; multi-gigabyte tensor payloads are left on disk for direct VRAM mapping via gguf_bridge.rs.

Structs

GGufSharder

Extracts the Ontological mapping and Lexicon from a raw GGUF file

GgufHyperparams

Architecture hyper-parameters parsed from the GGUF KV section.

GgufTensorIndex

Lookup table from tensor-name hash → GgufTensorInfo, built by walking the GGUF tensor-info section that immediately follows the KV metadata section.

GgufTensorInfo

Shape + type + offset for one tensor parsed from the GGUF tensor-info section.

GgufTokenizer

Vocabulary and BOS/EOS metadata extracted from a GGUF KV section. Used by infer_local_model() to encode prompts and decode output token IDs.

LayerTensors

Per-layer transformer weight metadata (all Option — absent tensors skipped).

PretokenSpan

Enums

ChatFamily

Chat-template family, detected from the special tokens a model’s vocab carries. Instruct models must have their prompt wrapped in this template (with an assistant-turn cue) or they degenerate (emit EOS immediately, or repeat) — a raw prompt gives the model no “your turn to answer” signal.

PretokenError

Constants

ARCH_DEEPSEEK_MOE

ARCH_FLAG_HAS_PLE

Feature flags on GgufHyperparams::arch_flags.

ARCH_FLAG_HAS_QK_NORM

ARCH_FLAG_HAS_SHARED_KV

ARCH_FLAG_HAS_SOFTCAP

ARCH_FLAG_HAS_SWA

ARCH_GEMMA

ARCH_GEMMA2

ARCH_GEMMA3

ARCH_GEMMA4

Gemma 4 (E2B/E4B/…): dual head-dim SWA+global, PLE, shared KV — not standard Llama-shape.

ARCH_GLM4

ARCH_LLAMA

ARCH_OTHER

ARCH_PHI4

ARCH_QWEN2

ARCH_UNKNOWN

Architecture id (stored in P64 hparams + used for support gating).

DEFAULT_ROPE_FREQ_BASE

Default RoPE base for Llama 3 / SmolLM2 when GGUF omits llama.rope.freq_base.

MAX_STOP_TOKEN_IDS

Max stop-token ids kept on the tokenizer (eos + chat-end family + extras).

Functions

parse_architecture_id

Map general.architecture GGUF string → [ARCH_*].

write_blk_tensor_name

Write blk.{layer}.{suffix} into out; returns total bytes written.