Related papers: MicroMix: Efficient Mixed-Precision Quantization w…

The evolution of quantization and mixed-precision techniques has unlocked new possibilities for enhancing the speed and energy efficiency of NNs. Several recent studies indicate that adapting precision levels across different parameters can…

Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved…

Large-scale language models (LLMs) excel in language processing tasks but face deployment challenges due to high memory and computational demands. While low-bit quantization, such as 4-bit techniques, offers a potential solution, these…

Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for…

In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as…

Post-training quantization (PTQ) has become an important technique for reducing the inference cost of Large Language Models (LLMs). While recent mixed-precision methods improve ultra-low bit quantization by preserving critical subspaces in…

The rapid growth of microcontroller-based IoT devices has opened up numerous applications, from smart manufacturing to personalized healthcare. Despite the widespread adoption of energy-efficient microcontroller units (MCUs) in the Tiny…

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we…

Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all experts into memory and activating multiple experts per…

Diffusion Transformer (DiT) has driven significant progress in image generation tasks. However, DiT inferencing is notoriously compute-intensive and incurs long latency even on datacenter-scale GPUs, primarily due to its iterative nature…

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…

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to…

The emerging trend of deploying complex algorithms, such as Deep Neural Networks (DNNs), increasingly poses strict memory and energy efficiency requirements on Internet-of-Things (IoT) end-nodes. Mixed-precision quantization has been…

In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackle this issue, which…

Quantization is an essential and popular technique for improving the accessibility of large language models (LLMs) by reducing memory usage and computational costs while maintaining performance. In this study, we apply 4-bit Group Scaling…

State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexity with the sequence length and demonstrates superior…

Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. Recent work on such…

The emergence of accurate open large language models (LLMs) has led to a race towards performant quantization techniques which can enable their execution on end-user devices. In this paper, we revisit the problem of "extreme" LLM…

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Large language models (LLMs) demand extensive memory capacity during both fine-tuning and inference. To enable memory-efficient fine-tuning, existing methods apply block-wise quantization techniques, such as NF4 and AF4, to the network…