Egor Maximov, Aleksei Merkelov, Vasiliy Alekseev, Ivan Krivorotov, Valentin Beliaev, Nikita Arsenin, Dmitry Bocharov, Aleksei Goncharov
Hybrid language models keep a key-value (KV) cache only in their few full-attention layers, but this cache is still the part of a prompt's state that grows with the prompt and that must be stored or moved to reuse it. We present DCKV, a differentiable codec for the KV cache and the first KV-cache codec that is trained end to end. Its transform, its quantizer and its entropy models, which are conditioned on the prompt tokens and on already decoded neighbouring positions, are optimized together against the frozen language model, both for the code length that the entropy models assign and for the change of the model's output. On Qwen3.5-2B, DCKV stores a compressed token in more than 55 times fewer bytes than bf16 at a loss of at most 1.8 points on three long-context benchmarks, and in more than 100 times fewer bytes at a loss of at most 3.6 points.
Egor Maximov, Yulia Kuzkina, Egor Shvetsov, Azamat Kanametov, Aleksandr Prutko, Maxim Zhelnin, Aleksei Goncharov
As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity methods, such as N:M sparsification, often fall short due to limited flexibility and sensitivity to outlier weights. We explore 8:16 semi-structured sparsity, demonstrating its ability to surpass the Performance Threshold—where a compressed model matches the accuracy of its uncompressed or smaller counterpart under equivalent memory constraints. Compared to 2:4 sparsity, 8:16 offers greater flexibility with minimal storage overhead (0.875 vs. 0.75 bits/element). We also apply sparse structured patterns for salient weights, showing that structured sparsity for outliers is competitive with unstructured approaches, leading to equivalent or better results. Finally, we demonstrate that simple techniques such as variance correction and SmoothQuant-like weight equalization improve sparse models performance.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表