Training
SparseGPT
Pruning / sparsityReferenceOne-shot layerwise unstructured pruning to 50% with error compensation.
- Relieves
- Capacity
- Targets
- Weights
- Format
- Unstructured sparsity
- Granularity
- Unstructured (≈50%)
- Structure
- unstructured
- Lifecycle
- PTQ · no gradients
- Calibration
- Small calibration set
- Compression
- ~2× (50% sparse)
- Quality
- Minimal loss at 50%; stacks before quant
- Hardware
- Sparse kernels for speedup, else capacity-only
- Runtimes
- Transformers
A worked Spark recipe for this method hasn't been written yet — it lives here as a reference point in the ontology.