Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

arXiv:2603.22324v1 Announce Type: cross Abstract: We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge

arXiv:2605.00422v1 Announce Type: cross Abstract: Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder

arXiv:2608.27875v1 Announce Type: new Abstract: Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit

arXiv:2609.04098v1 Announce Type: new Abstract: Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the

arXiv:2605.04084v1 Announce Type: cross Abstract: Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization

arXiv:2603.22370v1 Announce Type: cross Abstract: Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such

arXiv:2604.21743v1 Announce Type: new Abstract: Image enhancement models for mobile devices often struggle to balance high output quality with the fast processing speeds required

arXiv:2603.25284v1 Announce Type: new Abstract: In this paper, we address post-training quantization (PTQ) for large language models (LLMs) from an overlooked perspective: given a