2024
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
ACL 2024long
Self-attention is an essential component of large language models (LLM) but a significant source of inference latency for long sequences. In multi-tenant LLMs serving scenarios, the compute and memory operation cost of self-attention can be optimized by using the probability that multiple LLM reques…