[
    {
        "id": "osp-21045",
        "type": "article-journal",
        "title": "SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention",
        "author": [
            {
                "family": "Teng",
                "given": "Zihan"
            },
            {
                "family": "Zhao",
                "given": "Jiayu"
            },
            {
                "family": "Ren",
                "given": "Wentao"
            },
            {
                "family": "Fan",
                "given": "Minhao"
            },
            {
                "family": "Ma",
                "given": "Tianrui"
            },
            {
                "family": "Chen",
                "given": "Song"
            },
            {
                "family": "Liu",
                "given": "Weichen"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/slimkv-joint-token-feature-kv-cache-compression-with-reconstruction-free-beacon-attention",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compression strategies, token-wise methods reduce cached states but risk information loss through eviction or condensation, while feature-wise methods reduce per-token KV dimensions but can require full-dimensional reconstruction to apply positional embedding, limiting decoding speedups. We introduce SlimKV, a question-agnostic joint token-feature KV-cache compression method. SlimKV uses low-rank-aware training to compress long contexts into beacon memory states with latent KV representations, together with layer-adaptive rank allocation. We further uncover a positional asymmetry: removing key-side RoPE affects beacon and raw tokens differently, with much smaller degradation for beacon tokens. Exploiting this asymmetry, SlimKV trains beacon KV projections under a K-RoPE-free constraint and enables latent-space attention during decoding, mitigating reconstruction latency. On LongBench, SlimKV outperforms baselines at 16x/32x compression and remains leading at 4x/8x, where it retains over 96% of the uncompressed model's score. Needle-in-a-Haystack confirms robustness across evidence positions, and efficiency evaluation shows up to 7.34x attention speedup and 3.38x end-to-end decoding speedup over the uncompressed model at 128K length."
    }
]