TL;DR
A split-phase heterogeneous deployment strategy is proposed, and key optimization paths, including operator ecosystem completion and deep operator fusion, are identified.
This study presents the first comprehensive, cross-layer measurement study of mobile LLM inference, uniquely spanning five mainstream frameworks and three hardware backends, and identifies a distinct phase split where NPUs excel at compute-bound prefilling, while CPUs outperform all other backends in memory-bound decod...
Three fundamental design principles are revealed that provide design-space guidance for architects designing the next generation of memory-accelerated LLM systems.
HeteroMosaic first uses a heterogeneous roofline model to identify when combining iGPU and NPU execution is beneficial and decomposes inference into dependency-preserving micro-batches that expose cross-accelerator overlap and applies trace-guided co-optimization of scheduling and device allocation under practical effe...
Adaptive Sequence Pipeline Parallel Offloading (SPPO) is proposed, a novel framework that optimizes memory and computational resource efficiency for long-sequence LLM training and develops an adaptive pipeline scheduling approach with a heuristic solver and multiplexed sequence partitioning to improve computational res...
EPIC mitigates imbalance via performance-aware expert migration and runtime expert activation, and then improves communication with topology-adaptive transport kernels and fine-grained computation-communication overlap.
Results show that compact SLMs paired with PEFT provide a practical, energy-aware path to personalized on-device deployment, with the optimal method set by the dominant constraint: LoRA+ for energy and QLoRA for memory.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
