MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling
This addresses efficiency challenges for deploying large language models in long-context applications, with incremental improvements over existing sparse and linear attention methods.
The paper tackles the high computational and memory costs of Transformer-based LLMs for ultra-long contexts by introducing MiniCPM-SALA, a 9B-parameter hybrid architecture that integrates sparse and linear attention, achieving up to 3.5x inference speed at 256K tokens and supporting contexts up to 1M tokens.
The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention mechanisms attempt to mitigate these issues, they typically involve a trade-off between memory efficiency and model performance. This paper introduces MiniCPM-SALA, a 9B-parameter hybrid architecture that integrates the high-fidelity long-context modeling of sparse attention (InfLLM-V2) with the global efficiency of linear attention (Lightning Attention). By employing a layer selection algorithm to integrate these mechanisms in a 1:3 ratio and utilizing a hybrid positional encoding (HyPE), the model maintains efficiency and performance for long-context tasks. Furthermore, we introduce a cost-effective continual training framework that transforms pre-trained Transformer-based models into hybrid models, which reduces training costs by approximately 75% compared to training from scratch. Extensive experiments show that MiniCPM-SALA maintains general capabilities comparable to full-attention models while offering improved efficiency. On a single NVIDIA A6000D GPU, the model achieves up to 3.5x the inference speed of the full-attention model at the sequence length of 256K tokens and supports context lengths of up to 1M tokens, a scale where traditional full-attention 8B models fail because of memory constraints.