作者位次 #3/6ACL 2026Poster· Natural Language Processing
Resonating with R o PE : Spectral Quantization for High-Fidelity Key Cache Compression
Xuefei Wang · Haoyu Tang · Tianyuan Liang · Zhibin Wang · an Jiaotong University) · Weili Guan
摘要
The linear growth of KV cache bottlenecks long-context LLMs, yet RoPE-induced oscillations complicate Key cache quantization. To address this issue, we propose SpectrumQuant, a frequency-domain framework that utilizes the Discrete Cosine Transform (DCT) to convert these oscillations into sparse s...