相关论文: Hybrid Gated Flow (HGF): Stabilizing 1.58-bit LLMs…

Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, a post-training…

Deploying Large Language Models (LLMs) efficiently on edge devices is often constrained by limited memory capacity and high power consumption. Low-bit quantization methods, particularly ternary quantization, have demonstrated significant…

Low-bit weight-only quantization significantly reduces the memory footprint of large language models (LLMs), but disproportionately affects certain examples. We analyze diverse 3-4 bit methods on LLMs ranging from 7B-70B in size and find…

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

A large language model (LLM) is one of the most important emerging machine learning applications nowadays. However, due to its huge model size and runtime increase of the memory footprint, LLM inferences suffer from the lack of memory…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, yet they remain constrained by the finite capacity of their context windows and the inherent difficulty of maintaining long-term…

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minimizing per-layer…

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substantial memory, computational, and energy requirements of modern deep learning systems.…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy. However, challenges such as high computational and memory demands, heterogeneous client…

Large language models (LLMs) achieve remarkable performance but demand substantial computational resources, limiting deployment on edge devices and resource-constrained environments. We present TernaryLM, a 132M-parameter transformer…

Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open challenge. Current…

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

The severe on-chip memory limitations are currently preventing the deployment of the most accurate Deep Neural Network (DNN) models on tiny MicroController Units (MCUs), even if leveraging an effective 8-bit quantization scheme. To tackle…

Large Language Models (LLMs) possess a theoretical capability to model information density far beyond the limits of classical statistical methods (e.g., Lempel-Ziv). However, utilizing this capability for lossless compression involves…

Large language models (LLMs) suffer from proactive interference (PI): outdated information in the context window disrupts retrieval of current values. This interference degrades retrieval accuracy log-linearly as stale associations…

This paper investigates the challenging problem of learned image compression (LIC) with extreme low bitrates. Previous LIC methods based on transmitting quantized continuous features often yield blurry and noisy reconstruction due to the…