SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
paper
Fields
id
sources/quant-smoothquant-paperPublisher
arXiv
Kind
paper
Published
2022-11-18
Accessed
2026-10-03
notes
ICML 2023. v7 2024-03-29. | SOURCE AUDIT 2026-10-03: CONSOLIDATED: A second source record (qlab-smoothquant-paper) pointed at this same arXiv 2211.10438 URL and was cited by nothing; its notes read: "Read for the record that already exists; the offline outlier-migration alpha parameter is per-layer and non-default." The alpha detail is retained here; the redundant record was deleted.
Notes
ICML 2023. v7 2024-03-29. | SOURCE AUDIT 2026-10-03: CONSOLIDATED: A second source record (qlab-smoothquant-paper) pointed at this same arXiv 2211.10438 URL and was cited by nothing; its notes read: "Read for the record that already exists; the offline outlier-migration alpha parameter is per-layer and non-default." The alpha detail is retained here; the redundant record was deleted.
Cross-references
This record references no other records.