[Paper] Statistically-Lossless Quantization of Large Language Models

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

• PossiblePossibly related (embedding) · 61%$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space →
• PossiblePossibly related (embedding) · 60%bitsandbytes-foundation/bitsandbytes →
• PossiblePossibly related (embedding) · 57%The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs →
• PossiblePossibly related (embedding) · 57%QuantBench →
• PossiblePossibly related (embedding) · 55%Quantization →
• PossiblePossibly related (embedding) · 47%cvs-health/uqlm →

Covers

Covers (incoming)

Related across the graph