相关论文: BitSkip: An Empirical Analysis of Quantization and…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their extensive memory requirements, particularly due to KV cache growth during long-text understanding and…

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the…

Large Language Models (LLMs) stand out for their impressive performance in intricate language modeling tasks. However, their demanding computational and memory needs pose obstacles for broad use on edge devices. Quantization is then…

Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational efficiency becomes paramount. One of the major computational…

Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization…

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. While post-training quantization (PTQ) has successfully…

Multi-stage reasoning has emerged as an effective strategy for enhancing the reasoning capability of small language models by decomposing complex problems into sequential sub-stages. However, this comes at the cost of increased latency. We…

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…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…

In this paper, we present the first structural binarization method for LLM compression to less than 1-bit precision. Although LLMs have achieved remarkable performance, their memory-bound nature during the inference stage hinders the…

Auto-regressive Large Language Models (LLMs) demonstrate remarkable performance across different domains such as vision and language processing. However, due to sequential processing through a stack of transformer layers, autoregressive…

Binary quantization represents the most extreme form of compression, reducing weights to +/-1 for maximal memory and computational efficiency. While recent sparsity-aware binarization achieves sub-1-bit compression via weight pruning, it…

This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches…

We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fine-tuning methods for a budget of <4 bits. Pre-trained…

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across…

Building efficient inference framework has gained increasing interests for research community. Early-exit models, a variant of LLMs, improves the inference efficiency of LLMs by skipping rest layers and directly generate output tokens when…

Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large language models (LLMs) have recently been adopted for this task, as they provide strong…

Quantization reduces the numerical precision of Transformer computations and is widely used to accelerate inference, yet its effect on expressivity remains poorly characterized. We demonstrate a fine-grained theoretical tradeoff between…