howtospark
Training

AWQ

QuantizationReference

Protects the ~1% salient weights by activation scale; best-in-class INT4.

On the Spark

A solid default for W4A16 serving on vLLM.

Relieves
CapacityBandwidth
Targets
Weights
Format
INT4 (W4A16)
Granularity
Per-group (e.g. 128)
Lifecycle
PTQ · no gradients
Calibration
Small calibration set
Compression
~4×
Quality
≈FP16; beats GPTQ at the same bit-width
Hardware
Activation-aware INT4 kernels; broad GPU support
Runtimes
vLLMTensorRT-LLMSGLang

A worked Spark recipe for this method hasn't been written yet — it lives here as a reference point in the ontology.