AWhat changed
Used activation statistics and equivalent channel scaling to protect salient weight channels during low-bit weight-only quantization.
Scientific scope
Used activation statistics and equivalent channel scaling to protect salient weight channels during low-bit weight-only quantization. Year follows the 2023 preprint; MLSys publication was 2024. The technique and accompanying TinyChat system form one package; reported gains are workload- and hardware-specific.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Year follows the 2023 preprint; MLSys publication was 2024. The technique and accompanying TinyChat system form one package; reported gains are workload- and hardware-specific.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- MIT Han Lab: efficient model projects
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction