TAO: LLM 에이전트 서빙을 위한 툴 인식 스케줄링
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving
- 매체
- Hugging Face
- 게시
- 중요도
- 3/5
- 화제 지수
- 10
한국어 요약
아이테이오는 LLM 기반 에이전트 서빙의 지연 시간을 최대 26.8% 단축하는 툴 인식 조인트 스케줄링 프레임워크 TAO를 제안했다. TTFT는 최대 36.3% 개선되고 디코드 처리량은 최대 29.5% 증가했다.
원문 발췌 · English
Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness in service evaluation, wasting limited resources, and (2) use heuristic strategies to decide admission and placement on GPUs, resulting in suboptimal scheduling decisions. To bridge this gap, we present TAO, a tool-aware joint scheduling framework for LLM-based agentic serving. Its value interface combines near-term tool readiness, node-specific cache credit with time-aware decay, and token footprint; a dynamic program jointly selects and places waiting sessions under capacity constraints. Across the 12 reported model-workload-concurrency settings, TAO reduces latency by up to 26.8%, reduces mean time to first token (TTFT) by up to 36.3%, and increases decode throughput by up to 29.5% relative to the best evaluated state-of-the-art baseline for each metric.