RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference",
  "normalized_query": "2603.17891",
  "route": "/signal-canvas/ramp-reinforcement-adaptive-mixed-precision-quantization-for-efficient-on-device-llm-inference",
  "paper_ref": "ramp-reinforcement-adaptive-mixed-precision-quantization-for-efficient-on-device-llm-inference",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}