EdgeFM: Efficient Edge Inference for Vision-Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913075985121280 |
|---|---|
| author | Deng, Mengling Chen, Yuanpeng Yang, Sheng Tao, Wei Zhang, Wenhai Song, Hui Qin, Linyuanhao Zhao, Kai Ye, Xiaojun Mo, Shanhui Fan, Jingli Zhang, Shuang Liu, Bei Zhao, Tiankun An, Xiangjing |
| author_facet | Deng, Mengling Chen, Yuanpeng Yang, Sheng Tao, Wei Zhang, Wenhai Song, Hui Qin, Linyuanhao Zhao, Kai Ye, Xiaojun Mo, Shanhui Fan, Jingli Zhang, Shuang Liu, Bei Zhao, Tiankun An, Xiangjing |
| contents | Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource limitations. Existing frameworks either rely on bloated general-purpose designs or force developers into opaque, hardware-specific closed-source ecosystems, leading to hardware lock-in limitation and poor cross-platform adaptability. Observing that modern AI agents can efficiently search and tune configurations to generate highly optimized low-level kernels for standard LLM operators, we propose EdgeFM, a lightweight, agent-driven VLM/LLM inference framework tailored for cross-platform industrial edge deployment. EdgeFM removes non-essential features to reduce single-request latency, and encapsulates agent-tuned kernel optimizations as a modular library of reusable skills. By allowing direct invocation of these skills rather than waiting for closed-source implementations, it effectively closes the performance gap long dominated by proprietary toolchains. The framework natively supports mainstream platforms including x86 and NVIDIA Orin SoCs, and represents the first end-to-end VLA deployment on the domestic Horizon Journey platform, enhancing cross-platform portability. In most cases, it yields clearly better inference performance than conventional vendor-specific toolchains, achieving up to 1.49 times speedup over TensorRT-Edge-LLM on the NVIDIA Orin platform. Experimental results show that EdgeFM delivers favorable end-to-end inference performance, providing an open-source, production-grade solution for diverse edge industrial scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27476 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EdgeFM: Efficient Edge Inference for Vision-Language Models Deng, Mengling Chen, Yuanpeng Yang, Sheng Tao, Wei Zhang, Wenhai Song, Hui Qin, Linyuanhao Zhao, Kai Ye, Xiaojun Mo, Shanhui Fan, Jingli Zhang, Shuang Liu, Bei Zhao, Tiankun An, Xiangjing Computer Vision and Pattern Recognition Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource limitations. Existing frameworks either rely on bloated general-purpose designs or force developers into opaque, hardware-specific closed-source ecosystems, leading to hardware lock-in limitation and poor cross-platform adaptability. Observing that modern AI agents can efficiently search and tune configurations to generate highly optimized low-level kernels for standard LLM operators, we propose EdgeFM, a lightweight, agent-driven VLM/LLM inference framework tailored for cross-platform industrial edge deployment. EdgeFM removes non-essential features to reduce single-request latency, and encapsulates agent-tuned kernel optimizations as a modular library of reusable skills. By allowing direct invocation of these skills rather than waiting for closed-source implementations, it effectively closes the performance gap long dominated by proprietary toolchains. The framework natively supports mainstream platforms including x86 and NVIDIA Orin SoCs, and represents the first end-to-end VLA deployment on the domestic Horizon Journey platform, enhancing cross-platform portability. In most cases, it yields clearly better inference performance than conventional vendor-specific toolchains, achieving up to 1.49 times speedup over TensorRT-Edge-LLM on the NVIDIA Orin platform. Experimental results show that EdgeFM delivers favorable end-to-end inference performance, providing an open-source, production-grade solution for diverse edge industrial scenarios. |
| title | EdgeFM: Efficient Edge Inference for Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.27476 |