English

Scaling On-Device GPU Inference for Large Generative Models

Machine Learning 2025-05-02 v1 Artificial Intelligence

Abstract

Driven by the advancements in generative AI, large machine learning models have revolutionized domains such as image processing, audio synthesis, and speech recognition. While server-based deployments remain the locus of peak performance, the imperative for on-device inference, necessitated by privacy and efficiency considerations, persists. Recognizing GPUs as the on-device ML accelerator with the widest reach, we present ML Drift--an optimized framework that extends the capabilities of state-of-the-art GPU-accelerated inference engines. ML Drift enables on-device execution of generative AI workloads which contain 10 to 100x more parameters than existing on-device generative AI models. ML Drift addresses intricate engineering challenges associated with cross-GPU API development, and ensures broad compatibility across mobile and desktop/laptop platforms, thereby facilitating the deployment of significantly more complex models on resource-constrained devices. Our GPU-accelerated ML/AI inference engine achieves an order-of-magnitude performance improvement relative to existing open-source GPU inference engines.

Keywords

Cite

@article{arxiv.2505.00232,
  title  = {Scaling On-Device GPU Inference for Large Generative Models},
  author = {Jiuqiang Tang and Raman Sarokin and Ekaterina Ignasheva and Grant Jensen and Lin Chen and Juhyun Lee and Andrei Kulik and Matthias Grundmann},
  journal= {arXiv preprint arXiv:2505.00232},
  year   = {2025}
}

Comments

to be published in CVPR 2025 Workshop on Efficient and On-Device Generation (EDGE)

R2 v1 2026-06-28T23:17:32.334Z