Function quantize_binary 

pub fn quantize_binary(emb: &Vector) -> Result<QuantizedVector, QuantError>

Quantizes an embedding vector to binary (1-bit per value)

Binary quantization uses a simple threshold-based approach:

• Calculate the mean of all values
• Each value above mean → bit 1
• Each value below mean → bit 0

This is extremely lossy but preserves relative ordering and is fast for similarity.

Arguments

• emb - The embedding vector to quantize

Returns

• Ok(QuantizedVector) - Quantized vector with 32x compression
• Err(QuantError) - If quantization fails

Example

use lnmp_quant::binary::quantize_binary;
use lnmp_embedding::Vector;

let emb = Vector::from_f32(vec![0.1, -0.2, 0.3, -0.4]);
let quantized = quantize_binary(&emb).unwrap();
assert_eq!(quantized.scheme, lnmp_quant::QuantScheme::Binary);