MORI improves throughput 20-71% and TTFT 18-43% over baselines by ranking programs on a continuous idleness spectrum and shifting the GPU-CPU boundary to match capacity in agentic LLM serving.
Efficient llm serving for agentic workflows: A data systems perspective
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
Agentic workloads with context caching become decode-dominated with high KV-cache reuse and show tool use shifting from early read/explore to later execute/write phases.
Mix-Quant quantizes prefilling to NVFP4 and keeps BF16 for decoding in agentic LLMs, achieving up to 3x prefilling speedup while largely preserving task performance on long-context and agentic benchmarks.
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
Introduces a benchmarking suite with common workload adapters, event schemas, and an evidence gate connecting WebArena Verified, SWE-Gym, and MiniWoB++ for tool-using agents.
citing papers explorer
-
Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI
MORI improves throughput 20-71% and TTFT 18-43% over baselines by ranking programs on a continuous idleness spectrum and shifting the GPU-CPU boundary to match capacity in agentic LLM serving.
-
KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
-
Agentic AI Workload Characteristics
Agentic workloads with context caching become decode-dominated with high KV-cache reuse and show tool use shifting from early read/explore to later execute/write phases.
-
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
Mix-Quant quantizes prefilling to NVFP4 and keeps BF16 for decoding in agentic LLMs, achieving up to 3x prefilling speedup while largely preserving task performance on long-context and agentic benchmarks.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
-
An Executable Benchmarking Suite for Tool-Using Agents
Introduces a benchmarking suite with common workload adapters, event schemas, and an evidence gate connecting WebArena Verified, SWE-Gym, and MiniWoB++ for tool-using agents.