Module turboquant 

TurboQuant KV cache compression — CPU reference implementation.

Implements the TurboQuant_mse algorithm:

1. Walsh-Hadamard rotation for incoherence
2. Per-head norm extraction
3. Lloyd-Max scalar quantization against N(0,1) codebooks

This module is CPU-only math — no Metal GPU dispatch.

Structs

TurboQuantConfig

Configuration for TurboQuant quantization.

Enums

BitWidth

Quantization bit-width for TurboQuant.

Constants

CODEBOOK_2BIT

2-bit Lloyd-Max centroids for N(0,1): 4 reconstruction levels.

CODEBOOK_3BIT

3-bit Lloyd-Max centroids for N(0,1): 8 reconstruction levels.

CODEBOOK_4BIT

4-bit Lloyd-Max centroids for N(0,1): 16 reconstruction levels.

Functions

compute_lloyd_max_beta_codebook

Compute Lloyd-Max codebook for Beta((d-1)/2, (d-1)/2) scaled to [-1, 1].

compute_lloyd_max_codebook

Compute Lloyd-Max codebook for N(0,1) with the given number of levels.

fwht_inplace

In-place normalized Fast Walsh-Hadamard Transform.

turboquant_dequantize

Dequantize a TurboQuant-compressed head vector.

turboquant_quantize

Quantize a single head vector using TurboQuant_mse.