Guardado en:
Detalles Bibliográficos
Autor principal: Das, Anurita
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.21026
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • Deploying large language models to heterogeneous hardware is often constrained by memory, not compute. We introduce MCAP (Monte Carlo Activation Profiling), a load-time per-layer importance estimator that enables dynamic precision and memory placement decisions on the target device. MCAP produces a lightweight per-layer signal that drives both precision dispatch (W4A8 vs. W4A16) and residency tier (GPU, RAM, SSD), allowing a single set of weights to operate across diverse memory budgets. Our system, NVE, achieves 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 and enables models to run in memory regimes previously infeasible without modifying weights.