shantanuacharya
Abstract
Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation that improves computational efficiency by sharding attention across multiple hosts while minimizing communication overhead. In the first phase, the context is processed using blockwise-local attention across hosts, in parallel. In the second phase, query and response tokens attend to all prior cached tokens through sequence-global attention. Star Attention integrates seamlessly with most Transformer-based LLMs trained with global attention, reducing memory requirements and inference time by up to 11x while preserving 95-100% of accuracy.
Community
Star Attention is a novel block-sparse attention mechanism designed to enable efficient inference on long sequences in transformer-based LLMs. The method operates in two phases:
- Phase 1 - Context Encoding: The context tokens are processed using blockwise-local attention, with the context segmented into blocks where each block is prefixed with an anchor block.
- Phase 2 - Query Processing and Token Generation: The query and response tokens attend to all prior cached tokens through sequence-global attention.
Star Attention improves the inference time by up to 11x while preserving 95-100% of accuracy. The method is compatible with most Transformer-based LLMs trained with global attention, operating seamlessly out-of-the-box without additional training/finetuning.
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper