DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing

arXiv:2604.19351v1 Announce Type: new Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they often sacrifice generation quality and fail to address the high overhead of floating-point arithmetic. This paper introduces DASH-KV, an innovative acceleration framework that reformulates attention as approximate nearest-neighbor search via asymmetric deep hashing. Under this paradigm, we design an asymmetric encoding architecture that differentially maps queries and keys to account for their distinctions in precision and reuse characteristics. To balance efficiency and accuracy, we further introduce a dynamic mixed-precision mechanism that adaptively retains full-precision computation for critical tokens. Extensive experiments on LongBench demonstrate that DASH-KV significantly outperforms state-of-the-art baseline methods while matching the performance of full attention, all while reducing inference complexity from O(N^2) to linear O(N). The code is available at https://github.com/Zhihan-Zh/DASH-KV

Related

• AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
• Latent-Condensed Transformer for Efficient Long Context Modeling
• Compressing Sequences in the Latent Embedding Space: K-Token Merging for Large Language Models
• HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
• MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression

Source: arXiv cs.CL | 2026-04-22