conftrace_

layer-wise quantization

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model compression (3) large language model (2) variable quantization (1) attention reconstruction (1) layer importance (1) transformer model (1) bit allocation (1) bit precision (1) weight compression (1) mixed-precision quantization (1)

Papers

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers AAAI 2026 Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs ACL 2025 Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers NeurIPS 2024