Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related pathways. We present BIRDS, a framework for Biodiversity Impact of Request-Driven LLM Serving. BIRDS defines request-level functional units, quantifies operational and embodied biodiversity impact, and introduces Quality-Normalized Biodiversity Impact (QNBI) to jointly analyze ecological impact and response quality. Across diverse workloads, models, GPUs, and regions, BIRDS reveals that biodiversity impact accumulates at scale and exposes actionable quality-aware serving tradeoffs.

翻译：大型语言模型（LLM）服务对环境的影响不仅限于碳排放和水资源消耗，还包括通过生物多样性相关途径造成的生态系统损害。我们提出了BIRDS，一个面向请求驱动型LLM服务的生物多样性影响评估框架。BIRDS定义了请求级功能单元，量化了运营和隐含的生物多样性影响，并引入了质量归一化生物多样性影响（QNBI）以联合分析生态影响与响应质量。通过涵盖不同工作负载、模型、GPU和区域，BIRDS揭示了生物多样性影响随着规模扩大而累积的现象，并提供了可操作的、关注服务质量的服务权衡策略。