PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference Paper • 2610.19605 • Published 2 days ago • 2
PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference Paper • 2610.19605 • Published 2 days ago • 2
Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training Paper • 2505.11170 • Published May 16, 2025 • 3