arXiv:2606. 04063v1 Announce Type: cross Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements.
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources.
The paper introduces Llama-Mobile, a framework that quantizes vision‑language models for efficient mobile deployment. It uses a quantization pipeline that generates training data from the model itself, eliminating the need for the original training setup, and employs a novel 2.7‑bit‑per‑parameter format optimized for Arm CPUs. Applying this method, the authors compress the Llama 3.2 11B Vision Instruct model to 3.7 GB with 8‑bit activations while maintaining strong performance on visual question answering tasks.
Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.
arXiv:2607. 18081v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices.
arXiv:2605. 08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference.
arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
The paper introduces the "Compression Trinity," a unified framework that jointly applies sparsity, quantization, and low‑rank approximations to compress large language models. It presents several methods—MKOR, SLoPe, OPTIMA, PATCH, and SLiM—that leverage these three pillars to accelerate training, reduce memory bandwidth, and recover accuracy, achieving significant speedups and accuracy gains over existing techniques. The results demonstrate that combining all three compression strategies is essential for efficient, scalable, high‑performance LLM deployment.
arXiv:2510.08999v2 Announce Type: replace-cross Abstract: Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight...
arXiv:2608. 06916v1 Announce Type: new Abstract: Quantized Neural Networks~(QNN) with low-bitwidth data have proven promising in efficient storage and computation on edge devices.