SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips",
  "normalized_query": "2601.20309",
  "route": "/signal-canvas/superinfer-slo-aware-rotary-scheduling-and-memory-management-for-llm-inference-on-superchips",
  "paper_ref": "superinfer-slo-aware-rotary-scheduling-and-memory-management-for-llm-inference-on-superchips",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}