CSPS: A Communication-Efficient Sequence-Parallelism based Serving System for Transformer based Models with Long Prompts

Long-sequence generative large-language model (LLM) applications have become increasingly popular. In this paper, through trace-based experiments, we found that the existing method for long sequences results in a high Time-To-First-Token (TTFT) due to sequential chunk processing, long Time-Between-Tokens (TBT) from batching long-sequence prefills and decodes, and low throughput due to constrained key-value cache (KVC) for long sequences. To address these issues, we propose two Sequence-Parallelism (SP) architectures for both tensor parallelism (TP) and non-TP. However, SP introduces two challenges: 1) network communication and computation become performance bottlenecks; 2) the latter two issues above are mitigated but not resolved, and SP's resultant KV value distribution across GPUs still requires communication for decode, increasing TBT. Hence, we propose a Communication-efficient Sparse Attention (CSA) and communication-computation-communication three-phase pipelining. We also propose SP-based decode that processes decode separately from prefill, distributes KV values of a request across different GPUs, and novelly moves Query (Q) values instead of KV values to reduce communication overhead. These methods constitute a communication-efficient Sequence-Parallelism based LLM Serving System (SPS2). Our trace-driven evaluation demonstrates that SPS2 improves the average TTFT, TBT, and response time by up to 7.5x, 1.92x, and 9.8x and improves the prefill and decode throughput by 8.2x and 5.2x while maintaining the accuracy compared to Sarathi-Serve. We distributed our source code.