Small language models (SLMs) have emerged as a promising solution for deploying resource-constrained devices, such as smartphones and Web of Things. This work presents the first comprehensive study of over 60 SLMs such as Microsoft Phi and Google Gemma that are publicly accessible. Our findings show that state-of-the-art SLMs outperform 7B models in general tasks, proving their practical viability. However, SLMs’ in-context learning capabilities remain limited, and their efficiency has significant optimization potential. We identify key SLM optimization opportunities, including dynamic task-specific routing, model-hardware co-design, and vocabulary/KV cache compression. Overall, we expect the work to reveal an all-sided landscape of SLMs, benefiting the research community across algorithm, model, system, and hardware levels.

On-device Large Language Models (LLMs) are transforming mobile AI, catalyzing applications like UI automation without privacy concerns. Nowadays the common practice is to deploy a single yet powerful LLM as a general task solver for multiple requests. We identify a key system challenge in this paradigm: current LLMs lack the elasticity to serve requests that have diversified Service-Level Objectives (SLOs) on inference latency. To tackle this, we present ElastiLM, an on-device LLM service that elasticizes both the model and the prompt dimension of a full LLM. It incorporates (1) a one-shot neuron-reordering method, which leverages the intrinsic permutation consistency in transformer models to generate high-quality elasticized sub-models with minimal runtime switching overhead; (2) a dual-head tiny language model, which efficiently and effectively refines the prompt and orchestrates the elastification between model and prompt. We implement such an elastic on-device LLM service on multiple COTS smartphones, and evaluate ElastiLM on both standalone NLP/mobile-agent datasets and end-to-end synthesized traces. On diverse SLOs, ElastiLM outperforms 7 strong baselines in (absolute) accuracy by up to 14.83% and 10.45% on average, with <1% TTFT switching overhead, on-par memory consumption and <100 offline GPU hours.

Large language models (LLMs) such as GPTs and Mixtral-8x7B have revolutionized machine intelligence due to their exceptional abilities in generic ML tasks. Transiting LLMs from datacenters to edge devices brings benefits like better privacy and availability, but is challenged by their massive parameter size and thus unbearable runtime costs. To this end, we presentEdgeMoE, an on-device inference engine for mixture-of-expert (MoE) LLMs – a popular form of sparse LLM that scales its parameter size with almost constant computing complexity.EdgeMoEachieves both memory- and compute-efficiency by partitioning the model into the storage hierarchy: non-expert weights are held in device memory; while expert weights are held on external storage and fetched to memory only when activated. This design is motivated by a key observation that expert weights are bulky but infrequently used due to sparse activation. To further reduce the expert I/O swapping overhead,EdgeMoEincorporates two novel techniques: (1) expert-wise bitwidth adaptation that reduces the expert sizes with tolerable accuracy loss; (2) expert preloading that predicts the activated experts ahead of time and preloads it with the compute-I/O pipeline. On popular MoE LLMs and edge devices,EdgeMoEshowcase significant memory savings and speedup over competitive baselines.

DNNs are ubiquitous on edge devices nowadays. With its increasing importance and use cases, it's not likely to pack all DNNs into device memory and expect that each inference has been warmed up. Therefore, cold inference, the process to read, initialize, and execute a DNN model, is becoming commonplace and its performance is urgently demanded to be optimized. To this end, we present NNV12, the first on-device inference engine optimizing cold inference. NNV12 is built atop three novel optimization knobs: selecting a proper kernel (i.e., operator implementation) for each DNN operator, bypassing the weights transformation process by caching the post-transformed weights on disk, and pipelined execution of many kernels on asymmetric processors. To tackle with the huge search space, NNV12 employs a heuristic-based scheme to obtain a near-optimal kernel scheduling plan. We fully implement a prototype of NNV12 and evaluate its performance across extensive experiments. It shows that NNV12 achieves up to 15.2× speedup compared to the state-of-the-art DNN engines on edge CPUs and 401.5× speedup on edge GPUs, respectively.