- 入门指南
- 网络要求
- 单节点要求和安装
- 多节点要求和安装
- 安装后
- 配置 GPU
- 使用配置文件
- 节点调度
- 迁移和升级
- 基本故障排除指南
概述
Before choosing your deployment profile, see Supported use cases for single-node and multi-node installations.
单节点计算机要求
仅评估和演示场景支持此配置。
| 捆绑包 | 最低版本 | 推荐版本 |
|---|---|---|
| (v-)CPU 总计 | 16 (v-)CPU | 32 (v-)CPU |
| RAM | 52 GiB | 96 GiB |
| 每个节点的集群磁盘 | 256 GiB SSD 最低 IOPS:1100 | 256 GiB SSD 最低 IOPS:1100 |
| 数据磁盘 | 512 GiB SSD(用于在线) 1 TiB SSD(用于离线) 最低 IOPS 1100 | 2 TiB 固态硬盘 最低 IOPS 1100 |
| etcd 磁盘 | 16 GiB SSD 最低 IOPS:240 | 16 GiB SSD 最低 IOPS:240 |
| UiPath 捆绑包磁盘 (仅适用于在第一个服务器节点上的离线安装) | 512 GiB SSD 最低 IOPS:1100 | 512 GiB SSD 最低 IOPS:1100 |
Following the requirements above is enough for three skills and one pipeline running in parallel with the default configuration.
具有 GPU 支持的用于 Document Understanding 的其他代理节点
| 捆绑包 | 要求 |
|---|---|
| (v-)CPU | 8 (v-)CPU |
| RAM | 52 GiB |
| 集群磁盘 | 256 GiB SSD 最低 IOPS:1100 |
| 数据磁盘 | 不适用 |
| GPU RAM | 11 GiB |
Trainable Document Understanding ML Packages provided by UiPath will work on both CPU or GPU for datasets up to 500 images in size. GPU is strongly recommended to achieve faster training times and better model performance. Validation Station retraining loop is not supported on deployments without a GPU, due to the fact that dataset sizes increase too fast and may hit a compute wall with CPU very quickly. If you run UiPath Document OCR Local Server on AI Center to process more than 2 million pages of documents a year, GPU is strongly recommended for a better product experience.