Module encode 

Weight encoders: f32 in, GGUF block bytes out.

The rest of this crate reads quantized blocks. This module is the only place that writes them, and today it writes two formats: Q8_0 here, and Q4_K in q4_k. The rest is not an oversight, it is the scope: llama.cpp’s remaining K-quant and IQ encoders each need their own transcription (and, for the IQ tiers, a lattice search over a codebook), and a naive min/max encoder wearing a K-quant’s name produces a file that loads and generates measurably worse text. ferrox quantize refuses every target this module cannot encode, by name.

Each format lands with a byte-identical golden against llama.cpp’s own encoder, never a tolerance: two encoders can agree on dequantized values and still write different files.

Q8_0 here is byte-for-byte llama.cpp’s quantize_row_q8_0_ref, not merely “close enough”. The arithmetic below is deliberately the same shape as the C, including the reciprocal multiply and the a > b ? a : b maximum, because the file this writes is meant to be indistinguishable from llama-quantize --type Q8_0’s. See q8_0_matches_llama_cpp_quantize_row_q8_0_ref for the golden.

Modules

q4_k

The Q4_K weight encoder: a transcription of llama.cpp’s quantize_row_q4_K_ref (ggml/src/ggml-quants.c), not a reimplementation of it.

Functions

encode_block_q8_0

Encodes one Q8_0 block (exactly Q8_0_BLOCK_ELEMS values) and appends its Q8_0_BLOCK_BYTES bytes to out.

encode_row_q8_0

Encodes a whole row (or any slice whose length is a multiple of Q8_0_BLOCK_ELEMS) into Q8_0 blocks, appending to out.