Combining SmoothQuant-style channel scaling with QuaRot's Hadamard rotation reduces 4-bit weight-activation quantization error in LLMs by 10-30% of the gap to FP16.
SqueezeLLM: Dense-and-Sparse Quantization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs
Combining SmoothQuant-style channel scaling with QuaRot's Hadamard rotation reduces 4-bit weight-activation quantization error in LLMs by 10-30% of the gap to FP16.