howtospark
Training

Lossless weight coding (rANS / exponent codebook)

Reduce model sizeLossless codingReference

Entropy-code the weight bytes for a bit-exact ~1.5× shrink — no precision lost, unlike quantization.

On the Spark

The one shrink method with zero quality cost. BF16 sign+exponent fields take only ~31–56 distinct values per tensor, so rANS / a small exponent codebook recovers ~34% with an exact round-trip. On a bandwidth-bound Spark (273 GB/s) a fusible in-register decoder could cut bytes-per-token, not just disk. Research-stage (Brian Bell's weight-compression ledger); no turnkey Spark runtime yet.

Objective
Reduce model size · Lossless
Relieves
CapacityBandwidth
Targets
Weights
Format
Entropy-coded BF16 (rANS + exponent codebook)
Granularity
Per-tensor codebook, block-granular tiles
Lifecycle
PTQ · no gradients
Calibration
No calibration
Compression
~1.5× (BF16 → ~10.5 b/w)
Quality
100% — bit-exact round-trip
Hardware
In-register (fusible) decode kernels
Runtimes
In the wild
Lossless weight compression (Brian Bell)

Write-up on entropy-coding model weights for a bit-exact ~30% size reduction — no quality axis at all.

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