Lever: Speculative LLM Inference on Smartphones

• URL: http://arxiv.org/abs/2605.16786v1
• Date: Sat, 16 May 2026 03:43:10 GMT
• Title: Lever: Speculative LLM Inference on Smartphones
• Abstract summary: Large language models (LLMs) are increasingly needed for interactive mobile applications.<n>We present Lever, an end-to-end system for efficient flash-backed LLM inference on smartphones.
• Score: 11.768438191539374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage can hold larger models, yet flash-backed inference is slow because autoregressive decoding repeatedly invokes the target model and incurs costly I/O. We observe that speculative decoding is a natural fit for this setting: a small draft model can remain in DRAM, while a larger flash-resident target model verifies multiple candidate tokens per invocation. However, existing methods assume server-class accelerators and fail to account for prolonged I/O latency, limited computation parallelism, and irregular speculation execution. We present Lever, an end-to-end system for efficient flash-backed LLM inference on smartphones. Lever jointly optimizes the three stages of speculative decoding under mobile constraints. For drafting, it builds token trees using an I/O- and compute-aware gain-cost objective. For verification, it prunes low-value branches through early-exit prediction to reduce target-model computation. For execution, it maps speculation efficiently across mobile CPU-NPU hardware to improve utilization. Comprehensive evaluations show that Lever reduces inference latency by an average of 2.93x over baseline flash-offloaded inference and 1.50x over conventional speculative decoding, narrowing the latency gap between flash-backed and memory-resident LLM inference.

Related papers

• LLM Inference in a Flash! [66.43896490006965]
  Large Language Models (LLMs) have shown impressive capabilities across a range of natural language processing tasks.<n>We present an end-to-end integer-only quantization approach to eliminate expensive floating-point computations.
  arXiv  Detail & Related papers  (2026-09-14T18:04:30Z)
• Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding [51.48425605758328]
  We present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding.<n>FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning.<n>It achieves up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement.
  arXiv  Detail & Related papers  (2026-08-31T15:13:20Z)
• LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs [90.77662862634509]
  LiteFrame is a strong, yet highly efficient backbone for Video Large Language Models.<n>LiteFrame provides a 35% reduction in end-to-end latency while processing 8$times$ more frames.<n>Our results demonstrate a potential path to unlocking longer-form video understanding under fixed compute budgets.
  arXiv  Detail & Related papers  (2026-05-17T05:02:52Z)
• lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models [7.524517279167586]
  Large Language Models (LLMs) are increasingly integrated into everyday applications.<n>Running LLMs locally on mobile and edge devices (on-device LLMs) offers the promise of enhanced privacy, reliability, and reduced communication costs.<n>We propose lm-Meter, the first lightweight, online latency profiler tailored for on-device LLM inference.
  arXiv  Detail & Related papers  (2025-10-07T17:05:30Z)
• dParallel: Learnable Parallel Decoding for dLLMs [77.24184219948337]
  Diffusion large language models (dLLMs) offer parallel token prediction and lower inference latency.<n>Existing open-source models still require nearly token-length decoding steps to ensure performance.<n>We introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling.
  arXiv  Detail & Related papers  (2025-09-30T16:32:52Z)
• Democratizing Agentic AI with Fast Test-Time Scaling on the Edge [14.889726225226175]
  FlashTTS is a serving system that makes TTS practical for memory-constrained LLM reasoning.<n>Built as a plug-and-play library for vLLM, FlashTTS enables edge LLMs on a single consumer GPU to match the accuracy and latency of large cloud models.<n>Our evaluation demonstrates that FlashTTS achieves an average 2.2x higher goodput and reduces latency by 38%-68% compared to a vLLM baseline.
  arXiv  Detail & Related papers  (2025-08-29T19:12:04Z)
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [72.27673320976933]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding.<n>Current caching techniques accelerate decoding by storing full-layer states, yet impose substantial memory usage.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• SpecMemo: Speculative Decoding is in Your Pocket [7.062887337934677]
  Speculative decoding inherently relies on sacrificing extra memory allocations to generate several candidate tokens.<n>We present a device-aware inference engine named SpecMemo that can smartly control memory allocations at finer levels.<n>With SpecMemo's memory management, we maintain 96% of overall throughput from speculative decoding on MT-Bench.
  arXiv  Detail & Related papers  (2025-05-16T22:12:29Z)
• MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models [72.61076288351201]
  We propose Memory-efficient Offloaded Mini-sequence Inference (MOM)<n>MOM partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading.<n>On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU.
  arXiv  Detail & Related papers  (2025-04-16T23:15:09Z)
• Fast On-device LLM Inference with NPUs [10.80559106452755]
  We present llm.npu, the first LLM inference system utilizing on-device Neural Processing Unit (NPU) offloading to reduce prefill latency.<n>llm.npu enhances NPU offloading efficiency by re-constructing the prompt and model in three levels.<n>For the first time, llm.npu achieves more than 1,000 tokens/sec prefilling for a billion-sized model.
  arXiv  Detail & Related papers  (2024-07-08T12:20:45Z)
• S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs [7.816840847892339]
  Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. We propose Skippy Simultaneous Speculative Decoding (or S3D), a cost-effective self-speculative SD method based on simultaneous multi-token decoding and mid-layer skipping. Our method has achieved one of the top performance-memory ratios while requiring minimal architecture changes and training data.
  arXiv  Detail & Related papers  (2024-05-30T17:54:35Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [23.633481089469836]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance.<n>We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours.<n>Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.