arXiv:2606. 18114v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment.
arXiv:2608.20953v1 Announce Type: cross Abstract: Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and...
arXiv:2609.30820v1 Announce Type: cross Abstract: Looped transformers reuse weights across recurrence steps, making low-bit quantization especially attractive. We identify two distinct failure modes...
arXiv:2609.39223v2 Announce Type: new Abstract: Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive p...
In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes.
arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.
arXiv:2608.20873v1 Announce Type: new Abstract: Every way of teaching a deployed language model something new -- full fine-tuning, adapter merging, model editing -- replaces the released checkpoint,...
arXiv:2512. 18934v2 Announce Type: replace-cross Abstract: Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency.
arXiv:2606. 10932v1 Announce Type: cross Abstract: We present Density Field State Space Models (DF-SSM), a framework for compressing SSMs to a 1-bit scaffold with int8 low-rank correction.
The paper introduces DAMP, a decay‑aware mixed‑precision quantization scheme for recurrent‑state representations in GDN and KDA language models. By identifying high‑risk channels through quantization‑error energy and decay persistence, DAMP stores these channels at higher precision while compressing the rest to INT8, achieving a 9.9‑bit average precision. Experiments on Qwen3.6‑35B and Kimi‑Linear‑48B show a 69.1% reduction in recurrent‑state storage, up to 2.01× faster state‑update kernels, and up to 10.9% lower full‑model TPOT while preserving accuracy close to the FP32 baseline.
Post‑training quantization compresses large language models by storing weights at reduced precision, introducing errors into hidden states that could accumulate with depth. However, pretrained models accumulate far less hidden‑state error than randomly initialized ones, largely preserving downstream performance. The study identifies two key mechanisms: (1) each layer’s new error tends to oppose inherited error, partially canceling it, and (2) the LM‑head geometry preserves high‑rank token scores, mitigating output changes.
The paper presents a target‑centric survey of Quantization‑Aware Training (QAT), a technique that simulates quantization during model training to produce low‑bit models with accuracy comparable to full‑precision ones. It systematically reviews existing QAT methods using a target‑centric taxonomy, highlighting differences in error characteristics, numerical formats, and strategy transferability across targets. The survey also summarizes QAT evaluation paradigms, discusses optimization and deployment challenges, and outlines potential future research directions.
arXiv:2608.28809v1 Announce Type: new Abstract: Extreme low-bit inference offers a route toward smaller models and constrained deployment. Ternary language models restrict weights to $\{-1,0,+1\}$, a...