Scaling Shapley Energy Attribution to Large LLM Batches
cs.DC, cs.AR, cs.PF
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving
- Measuring the environmental impact of delivering AI at Google Scale
- Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum
- Gemma 4 Technical Report
- Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection
- Request-Level Energy Attribution for Batched LLM Serving
- gpt-oss-120b & gpt-oss-20b Model Card
- Qwen2.5 Technical Report
- Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms
- BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems
- Qwen3 Technical Report
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends