相关论文: ZeroQuant: Efficient and Affordable Post-Training …

Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. Several existing sub 2-bit post-training quantization (PTQ) methods utilize a mix-precision scheme by leveraging an…

Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI…

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight…

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

Post-training quantization (PTQ) compresses the weights and activations of large language models (LLMs) into low-precision representations to reduce memory footprint and accelerate inference. However, the presence of outliers in weights and…

Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. However, the computational cost for deploying these models is…

Mixture-of-Experts (MoE) models enable scalable computation and performance in large-scale deep learning but face quantization challenges due to sparse expert activation and dynamic routing. Existing post-training quantization (PTQ) methods…

We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit…

Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression…

Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight quantization is the standard tool for acceleration, but…

Post-training quantization (PTQ) has emerged as a critical technique for efficient deployment of large language models (LLMs). This work proposes NestQuant, a novel PTQ scheme for weights and activations that is based on self-similar nested…

The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training and during fine-tuning, applying quantization in…

Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even…

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Pretraining transformers are generally time-consuming. Fully quantized training (FQT) is a promising approach to speed up pretraining. However, most FQT methods adopt a quantize-compute-dequantize procedure, which often leads to suboptimal…

Large language models(LLMs) exhibit excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. However, existing…

The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…

Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (FP16, INT8, INT4) and…

Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly matched to a low-bit…