Similar Items: Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel
- LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling
- PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
- Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference
- Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
- ADELIA: Automatic Differentiation for Efficient Laplace Inference Approximations
- SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters