Block-Attention for Efficient Prefilling

We introduce Block-attention, an attention mechanism designed to address the increased inference latency and cost in Retrieval-Augmented Generation (RAG) scenarios. Traditional approaches often encode the entire context in an autoregressive manner. Instead, Block-attention divides retrieved documents into discrete blocks, with each block independently calculating key-value (KV) states except for the final block. In RAG scenarios, by defining each passage as a block, Block-attention enables us to reuse the KV states of passages that have been seen before, thereby significantly reducing the latency and the computation overhead during inference. The implementation of Block-attention involves block segmentation, position re-encoding, and fine-tuning the LLM to adapt to the Block-attention mechanism. Experiments on 11 diverse benchmarks, including RAG, ICL, and general domains, demonstrate that after block fine-tuning, the Block-attention model not only achieves performance comparable to that of fullattention models, but can also seamlessly switch between the block and full attention modes without any performance loss. Notably, Block-attention significantly reduces the time to first token (TTFT) and floating point operations (FLOPs) to a very low level. It only takes 45 ms to output the first token for an input sequence with a total length of 32K. Compared to the full-attention models, the TTFT and corresponding FLOPs are reduced by 98.7% and 99.8%, respectively. Additionally, in Appendix A, we elaborate on how Block-attention is applied in Game AI scenario and the substantial potential benefits it entails. We strongly suggest researchers in the gaming field not to overlook this section. 1 * Equal Contribution † Corresponding Author 1 Codes, datasets and model weights have been publicly available at https://github.com/ TemporaryLoRA/Block-attention .