发现大模型提示词中可并行处理的隐藏结构，提速最高5倍。
PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries
- 通过分析真实用户提示，提取可并行的任务结构
- 75%以上提示能成功分解，任务速度最高提升5倍
- 适合研究大模型推理优化与系统设计的开发者
大模型服务系统通常将用户提示视为单一输入，通过解码技巧或跨查询批量处理进行优化。然而，许多真实提示中存在潜在的语义并行性——可分解的结构，使子任务独立执行，在保持语义不变的前提下降低延迟。我们提出PARALLELPROMPT，首个衡量自然用户提示内并行性的基准。数据集包含超过3.7万条来自公开LLM聊天日志的真实提示，每条均标注了任务模板、共享上下文和迭代输入的结构化信息，通过大模型辅助提示结合规则化多语言验证提取。为评估分解收益，我们提供执行套件，对比串行与并行策略在延迟、结构保真度和语义一致性上的表现。结果表明，75%以上的精选提示可成功解析出内查询并行性，在翻译、理解与比较分析等任务中实现最高5倍加速，且质量损失极小。通过发布该基准、清洗流程与评估套件，我们首次提供标准化测试平台，用于研究大模型服务中的结构感知执行。
原文摘要 · Abstract (English)
LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contain latent semantic parallelism--decomposable structures where subtasks can be executed independently to reduce latency while preserving meaning. We introduce PARALLELPROMPT, the first benchmark for measuring intra-query parallelism in natural user prompts. Our dataset comprises over 37,000 real-world prompts from public LLM chat logs, each annotated with a structured schema capturing task templates, shared context, and iteration inputs. These schemas are extracted using LLM-assisted prompting with rule-based multilingual validation. To evaluate the benefits of decomposition, we provide an execution suite that benchmarks serial vs. parallel strategies, measuring latency, structural adherence, and semantic fidelity. Our results show that intra-query parallelism can be successfully parsed in over 75% of curated datasets, unlocking up to 5x speedups on tasks like translation, comprehension, and comparative analysis, with minimal quality degradation. By releasing this benchmark, curation pipeline, and evaluation suite, we provide the first standardized testbed for studying structure-aware execution in LLM serving pipelines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。