Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference

• URL: http://arxiv.org/abs/2505.06461v1
• Date: Fri, 09 May 2025 23:05:53 GMT
• Title: Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference
• Authors: Haolin Zhang, Jeff Huang,
• Abstract summary: We show that a CPU-only configuration achieves 17 tokens per second, surpassing the 12.8 tokens per second obtained with GPU acceleration.<n>We analyze the factors driving this counterintuitive result, revealing that GPU memory transfer overhead and CPU thread optimization play a critical role.<n>Our findings challenge conventional GPU-first thinking, highlighting the untapped potential of optimized CPU inference.
• Score: 6.829272097221596
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The common assumption in on-device AI is that GPUs, with their superior parallel processing, always provide the best performance for large language model (LLM) inference. In this work, we challenge this notion by empirically demonstrating that, under certain conditions, CPUs can outperform GPUs for LLM inference on mobile devices. Using a 1-billion-parameter LLM deployed via llama.cpp on the iPhone 15 Pro, we show that a CPU-only configuration (two threads, F16 precision) achieves 17 tokens per second, surpassing the 12.8 tokens per second obtained with GPU acceleration. We analyze the architectural factors driving this counterintuitive result, revealing that GPU memory transfer overhead and CPU thread optimization play a critical role. Furthermore, we explore the impact of thread oversubscription, quantization strategies, and hardware constraints, providing new insights into efficient on-device AI execution. Our findings challenge conventional GPU-first thinking, highlighting the untapped potential of optimized CPU inference and paving the way for smarter deployment strategies in mobile AI. However, fully explaining the observed CPU advantage remains difficult due to limited access to low-level profiling tools on iOS.

Related papers

• CUDA-LLM: LLMs Can Write Efficient CUDA Kernels [9.287036563375617]
  Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation.<n>We propose a novel framework called textbfFeature SearchReinforcement (FSR) FSR jointly optimize compilation and functional correctness.
  arXiv  Detail & Related papers  (2025-06-10T10:51:03Z)
• DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference [14.676716521856813]
  Mixture-of-Experts (MoE) models face significant deployment challenges on memory-constrained devices.<n>We presentP, an on-device MoE inference engine to optimize parallel GPU- CPU execution.<n>P outperforms traditional expert caching and prefetching methods by up to 8.20x and offloading techniques by 1.35x while maintaining accuracy.
  arXiv  Detail & Related papers  (2024-12-16T07:59:21Z)
• ThunderKittens: Simple, Fast, and Adorable AI Kernels [43.32681787348603]
  We present ThunderKittens (TK), a framework for writing performant AI kernels while remaining easy to use and maintain. We show the value of TK by providing kernels that match or outperform prior kernels for a range of AI operations.
  arXiv  Detail & Related papers  (2024-10-27T10:07:16Z)
• Benchmarking Edge AI Platforms for High-Performance ML Inference [0.0]
  Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often involve scaling down modern hardware, the performance characteristics of neural network workloads can vary significantly. We compare the latency and throughput of various linear algebra and neural network inference tasks across CPU-only, CPU/GPU, and CPU/NPU integrated solutions.
  arXiv  Detail & Related papers  (2024-09-23T08:27:27Z)
• FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs [57.12856172329322]
  We envision a decentralized system unlocking the potential vast untapped consumer-level GPU. This system faces critical challenges, including limited CPU and GPU memory, low network bandwidth, the variability of peer and device heterogeneity.
  arXiv  Detail & Related papers  (2023-09-03T13:27:56Z)
• Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures [67.47328776279204]
  This work introduces a framework to develop efficient, portable Deep Learning and High Performance Computing kernels. We decompose the kernel development in two steps: 1) Expressing the computational core using Processing Primitives (TPPs) and 2) Expressing the logical loops around TPPs in a high-level, declarative fashion. We demonstrate the efficacy of our approach using standalone kernels and end-to-end workloads that outperform state-of-the-art implementations on diverse CPU platforms.
  arXiv  Detail & Related papers  (2023-04-25T05:04:44Z)
• FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU [89.2451963569343]
  FlexGen is a generation engine for running large language model (LLM) inference on a single commodity GPU. When running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems. On the HELM benchmark, FlexGen can benchmark a 30B model with a 16GB GPU on 7 representative sub-scenarios in 21 hours.
  arXiv  Detail & Related papers  (2023-03-13T05:19:28Z)
• MAPLE-Edge: A Runtime Latency Predictor for Edge Devices [80.01591186546793]
  We propose MAPLE-Edge, an edge device-oriented extension of MAPLE, the state-of-the-art latency predictor for general purpose hardware. Compared to MAPLE, MAPLE-Edge can describe the runtime and target device platform using a much smaller set of CPU performance counters. We also demonstrate that unlike MAPLE which performs best when trained on a pool of devices sharing a common runtime, MAPLE-Edge can effectively generalize across runtimes.
  arXiv  Detail & Related papers  (2022-04-27T14:00:48Z)
• PLSSVM: A (multi-)GPGPU-accelerated Least Squares Support Vector Machine [68.8204255655161]
  Support Vector Machines (SVMs) are widely used in machine learning. However, even modern and optimized implementations do not scale well for large non-trivial dense data sets on cutting-edge hardware. PLSSVM can be used as a drop-in replacement for an LVM.
  arXiv  Detail & Related papers  (2022-02-25T13:24:23Z)
• Enabling On-Device Smartphone GPU based Training: Lessons Learned [10.420617367363047]
  We conduct an initial analysis to examine the feasibility of on-device training on smartphones using mobile GPUs. To solve the bottleneck, we optimize the OpenCL backend's kernels, showing 2x improvements (40-70 GFLOPs) over CPUs. The data movement takes almost 91% of training time due to the low bandwidth.
  arXiv  Detail & Related papers  (2022-02-21T10:29:16Z)
• MAPLE: Microprocessor A Priori for Latency Estimation [81.91509153539566]
  Modern deep neural networks must demonstrate state-of-the-art accuracy while exhibiting low latency and energy consumption. Measuring the latency of every evaluated architecture adds a significant amount of time to the NAS process. We propose Microprocessor A Priori for Estimation Estimation MAPLE that does not rely on transfer learning or domain adaptation.
  arXiv  Detail & Related papers  (2021-11-30T03:52:15Z)
• Kernel methods through the roof: handling billions of points efficiently [94.31450736250918]
  Kernel methods provide an elegant and principled approach to nonparametric learning, but so far could hardly be used in large scale problems. Recent advances have shown the benefits of a number of algorithmic ideas, for example combining optimization, numerical linear algebra and random projections. Here, we push these efforts further to develop and test a solver that takes full advantage of GPU hardware.
  arXiv  Detail & Related papers  (2020-06-18T08:16:25Z)

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.