A parametric cubic codebook with two shape parameters per group reduces quantization reconstruction error versus uniform integer and finite floating-point baselines for 1-8-bit LLM weights, and can be executed directly from packed weights on GPUs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights
A parametric cubic codebook with two shape parameters per group reduces quantization reconstruction error versus uniform integer and finite floating-point baselines for 1-8-bit LLM weights, and can be executed directly from packed weights on GPUs.