Training
AQLM / QuIP# (2-bit codebook)
QuantizationReferenceCodebook / vector quantization pushing weights toward ~2 bits.
- Relieves
- Capacity
- Targets
- Weights
- Format
- 2-bit vector / codebook
- Granularity
- Vector quantization
- Lifecycle
- PTQ · no gradients
- Calibration
- Full corpus
- Compression
- ~8× (2-bit)
- Quality
- Usable at 2-bit; below 4-bit methods
- Hardware
- Custom codebook decode kernels
- Runtimes
- vLLMTransformers
A worked Spark recipe for this method hasn't been written yet — it lives here as a reference point in the ontology.