SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality

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

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:2603.18567v1 Announce Type: cross Abstract: Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates

arXiv:2604.04988v1 Announce Type: cross Abstract: Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression

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: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