5 papers
LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
Jinwoo Ahn, Ingyu Seong, Akhil Kedia +4
Transformer-based large language models (LLMs) rely on key-value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves…
On the Importance of a Multi-Scale Calibration for Quantization
Seungwoo Son, Ingyu Seong, Junhan Kim +2
Post-training quantization (PTQ) is a cornerstone for efficiently deploying large language models (LLMs), where a small calibration set critically affects quantization performance.…
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
Junhan Kim, Yeo Jeong Park, Seungwoo Son +4
The rapid growth of large language models (LLMs) has heightened the importance of post-training quantization (PTQ) for reducing memory and computation costs. Among PTQ methods, GPT…
Two-Stage Grid Optimization for Group-wise Quantization of LLMs
Junhan Kim, Gukryeol Lee, Seungwoo Son +2
Group-wise quantization is an effective strategy for mitigating accuracy degradation in low-bit quantization of large language models (LLMs). Among existing methods, GPTQ has been…
BoA: Attention-aware Post-training Quantization without Backpropagation
Junhan Kim, Ho-young Kim, Eulrang Cho +3
Post-training quantization (PTQ) is a promising solution for deploying large language models (LLMs) on resource-constrained devices. Early methods developed for small-scale network…