arXiv:2607. 05475v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency.
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv:2606. 11257v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation.
arXiv:2504. 08791v3 Announce Type: replace-cross Abstract: On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability.
arXiv:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
The paper introduces Routide, a Swift/MLX runtime that runs a quantized Qwen3.6-35B-A3B model on iPhone by keeping expert weights on device storage and a byte‑budgeted subset in memory. It evaluates cache‑policy effects, showing that a 512 MiB LRU cache yields 0.00% demand hits while a 576 MiB LRU reaches 38.58% hits across five 128‑token workloads, indicating that capacity limits depend on policy and workload. The study also reports memory footprints, thermal events, and power estimates, demonstrating that flash‑backed MoE inference is feasible within bounded resources but has measurable limitations.
In large language model (LLM) serving systems, the key-value (KV) cache grows linearly with sequence length and concurrency, so long-context inference easily hits the high-bandwidth memory (HBM) capac...
arXiv:2611.07542v1 Announce Type: new Abstract: In large language model (LLM) serving systems, the key-value (KV) cache grows linearly with sequence length and concurrency, so long-context inference...
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
LeanStream introduces a speculate‑and‑refine streaming framework that enables efficient on‑device inference of large language models by progressively refining computation, loading, and cache‑retention priorities using partial GPU results. This approach allows fine‑grained overlap between GPU execution and storage I/O, avoiding the trade‑offs of existing systems that serialize execution or incur redundant weight fetches. Implemented on mobile and embedded platforms, LeanStream reduces memory usage by 4.8× to 7.5× compared to prior work while improving token generation throughput by 1.6× to 2.1×.
arXiv:2606. 28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.
arXiv:2606. 00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency.