相关论文: FAQ: Mitigating Quantization Error via Regeneratin…

We study weight-only post-training quantization (PTQ), which quantizes the weights of a large language model (LLM) without retraining, using little or no calibration data. Weight-only PTQ is crucial for reducing the memory footprint and…

Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are…

Permanent faults induced due to imperfections in the manufacturing process of Deep Neural Network (DNN) accelerators are a major concern, as they negatively impact the manufacturing yield of the chip fabrication process. Fault-aware…

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quantization-aware training (QAT) are well studied in the context…

Post-training quantization (PTQ) has recently emerged as an effective tool for reducing the computational complexity and memory usage of a neural network by representing its weights and activations with lower precision. While this paradigm…

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used…

Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on a few calibration dataset-free quantization methods suggest…

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,…

QLoRA reduces the memory-cost of fine-tuning a large language model (LLM) with LoRA by quantizing the base LLM. However, quantization introduces quantization errors that negatively impact model performance after fine-tuning. In this paper…

Post-training quantization (PTQ) of large language models (LLMs) holds the promise in reducing the prohibitive computational cost at inference time. Quantization of all weight, activation and key-value (KV) cache tensors to 4-bit without…

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask…

Post-training quantization (PTQ) is a promising solution for deploying large language models (LLMs) on resource-constrained devices. Early methods developed for small-scale networks, such as ResNet, rely on gradient-based optimization,…

Quantization-aware training (QAT) schemes have been shown to achieve near-full precision accuracy. They accomplish this by training a quantized model for multiple epochs. This is computationally expensive, mainly because of the full…

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on integer quantization,…

Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's effects on various LLM capabilities have been extensively studied, one critical area remains…

Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment. Ternarization has gained attention as a promising compression technique, delivering…

Quantization has gained attention as a promising solution for the cost-effective deployment of large and small language models. However, most prior work has been limited to perplexity or basic knowledge tasks and lacks a comprehensive…

The growing use of large language models has raised environmental and economic concerns about their intensity of resource usage during inference. Serving these models to each user requires substantial energy and water for cooling. Model…

Latent Diffusion Models (LDMs) capture the dynamic evolution of latent variables over time, blending patterns and multimodality in a generative system. Despite the proficiency of LDM in various applications, such as text-to-image…