TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

infrastructure

Two-Bit Weights Met the Cost of Their Decoder

A full multi-shell Leech-lattice decoder exposes the gap between compact on-disk weights and the bytes a serving kernel actually reads.

Published Updated Story ID: mp-2026-09-03-008
Read the complete editionStory JSON

Summary

A full multi-shell Leech-lattice decoder exposes the gap between compact on-disk weights and the bytes a serving kernel actually reads.

The implementation expands a 301-class codebook into GPU layouts and fuses dequantization with matrix-vector multiplication for batch-one decoding. Binary bit planes beat one-hot masks, but the served layout still read 2.40× more bytes and ran 2.27× slower than the compared trellis kernel. With a shared output head, end-to-end gains rose from 1.11× at 4B to 1.41× at 14B, while the 4B quality cost remained substantial, underscoring that nominal bit rate is not the whole serving story.

Why it matters

A full multi-shell Leech-lattice decoder exposes the gap between compact on-disk weights and the bytes a serving kernel actually reads.

Limits and context

  • With a shared output head, end-to-end gains rose from 1.11× at 4B to 1.41× at 14B, while the 4B quality cost remained substantial, underscoring that nominal bit rate is not the whole serving story.

Key claims

  1. A full multi-shell Leech-lattice decoder exposes the gap between compact on-disk weights and the bytes a serving kernel actually reads.

    Qualification: With a shared output head, end-to-end gains rose from 1.11× at 4B to 1.41× at 14B, while the 4B quality cost remained substantial, underscoring that nominal bit rate is not the whole serving story.

    Evidence: source-2026-09-03-008

Sources

  1. arXiv preprint 2609.02652arXiv · primary research

Corrections

No corrections have been recorded for this story.