Skip to content
conftrace_

attention reconstruction

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

layer-wise quantization (1) transformer model (1) large language model (1) attention module (1) edge deployment (1) post-training quantization (1) model compression (1)

Papers

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers NeurIPS 2024