paper-with-me

Papers

Does quantization affect models' performance on long-context tasks?

2025-05-26 · Anmol Mekala, Anirudh Atmakuru, Yixiao Song, Marzena Karpinska, Mohit Iyyer

Large language models (LLMs) now support context windows exceeding 128K tokens, but this comes with significant memory requirements and high inference latency. Quantization can mitigate these costs, but may degrade performance. In this work, we present the first systematic evaluation of quantized LLMs on tasks with long-inputs (>64K tokens) and long-form outputs. Our evaluation spans 9.7K test examples, five quantization methods (FP8, GPTQ-int8, AWQ-int4, GPTQ-int4, BNB-nf4), and five models (Llama-3.1 8B and 70B; Qwen-2.5 7B, 32B, and 72B). We find that, on average, 8-bit quantization preserves accuracy (~0.8% drop), whereas 4-bit methods lead to substantial losses, especially for tasks involving long context inputs (drops of up to 59%). This degradation tends to worsen when the input is in a language other than English. Crucially, the effects of quantization depend heavily on the quantization method, model, and task. For instance, while Qwen-2.5 72B remains robust under BNB-nf4, Llama-3.1 70B experiences a 32% performance drop on the same task. These findings highlight the importance of a careful, task-specific evaluation before deploying quantized LLMs, particularly in long-context scenarios and with languages other than English.

📄 PDF Abstract BibTeX arXiv:2505.20276

Code (1)

molereddy/long-context-quantization 공식 구현

Tasks

Quantization

Similar Papers 제목 키워드 기반

The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs

2024-06-10 · Mert Yazan, Suzan Verberne, Frederik Situmeang

Post-training quantization reduces the computational demand of Large Language Models (LLMs) but can weaken some of their capabilities. Since LLM abilities emerge with scale, smaller LLMs are more sensitive to quantizatio…

QuantizationRAGRetrievalRetrieval-augmented Generation

Designing strong baselines for ternary neural network quantization through support and mass equalization

2023-06-30 · Edouard Yvinec, Arnaud Dapogny, Kevin Bailly

Deep neural networks (DNNs) offer the highest performance in a wide range of applications in computer vision. These results rely on over-parameterized backbones, which are expensive to run. This computational burden can …

Quantization

How Does Quantization Affect Multilingual LLMs?

2024-07-03 · Kelly Marchisio, Saurabh Dash, Hongyu Chen, Dennis Aumiller 외

Quantization techniques are widely used to improve inference speed and deployment of large language models. While a wide body of work examines the impact of quantization on LLMs in English, none have evaluated across lan…

Mathematical ReasoningQuantization

KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache

2025-05-18 · Fei Li, Song Liu, Weiguo Wu, Shiqiang Nie 외

The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the me…

Quantization

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering

2025-06-05 · Vinay Joshi, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum

The key-value (KV) cache in transformer models is a critical component for efficient decoding or inference, yet its memory demands scale poorly with sequence length, posing a major challenge for scalable deployment of la…

Quantization