Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement
arXiv:2609.25916v1 Announce Type: cross Abstract: Mixed-precision weight quantization is commonly formulated as a Multiple-Choice Knapsack Problem (MCKP), yet existing solvers rely on scalar sensitivity proxies that collapse each weight matrix's Hessian into a single number and treat every module i…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-23 04:00 · arXiv stat.ML
Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement