TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference
TELLER:面向大语言模型推理的非侵入式跨层根因分析
专题命中 效率与部署 :LLM(title,summary_cn);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG
AI总结 TELLER是面向LLM推理的非侵入式跨层根因分析框架,通过跟踪与日志结合实现异常定位与自然语言解释,在多节点GPU工作负载上兼具高效压缩与诊断性能,为LLM推理RCA提供实用支撑。
Comments 12 pages, 1 figure, 9 tables. Accepted to the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)