veloxquant_mlx.quantizers.base module

Quantizer construction entry point: QuantizerFactory.

Provides the single sanctioned way to instantiate a fixed-bit-width KV quantizer (QJL, TurboQuant MSE/Prod, PolarQuant, …) by algorithm name, validating shared preconditions (power-of-two dimension, bit-width >= 1) before dispatching to the class registered under that name in QuantizerRegistry.

class veloxquant_mlx.quantizers.base.QuantizerFactory[source]

Bases: object

Factory for creating Quantizer instances via the QuantizerRegistry.

All quantizer construction should go through this factory.

Example:

q = QuantizerFactory.create("qjl", d=128, m=128, seed=42)
q = QuantizerFactory.create("turboquant_mse", d=128, b=2, seed=42)
q = QuantizerFactory.create("turboquant_prod", d=128, b=3, m=128, seed=42)
q = QuantizerFactory.create("polar", d=128, b=2, seed=42)
static create(method, d, b=2, m=None, seed=42, store=None, **kwargs)[source]

Instantiate a Quantizer by method name.

Parameters:

  • method (Literal['qjl', 'turboquant_mse', 'turboquant_prod', 'polar']) – Algorithm name registered in QuantizerRegistry.

  • d (int) – Vector dimension.

  • b (int) – Bit-width (default 2).

  • m (int | None) – JL projection dimension (default = d for QJL methods).

  • seed (int) – Random seed.

  • store (ArtifactStore | None) – ArtifactStore for loading precomputed artifacts. If None, artifacts are generated on-the-fly.

  • **kwargs (Any) – Additional keyword arguments forwarded to the quantizer.

Return type:

Quantizer

Returns:

Configured Quantizer instance.

Raises: