Similar Items: Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
- LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling
- Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference
- PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
- FATE: Future-State-Aware Scheduling for Heterogeneous LLM Workflows
- Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel
- CLAD: A Clustered Label-Agnostic Federated Learning Framework for Joint Anomaly Detection and Attack Classification