算力商业
developer.nvidia.com ·
@Tanya Lenz
借助 Global Performance Tuner 扩展 NVIDIA TensorRT 性能优化：超越单一构建路径（第一部分）
NVIDIA 开发者博客指出，部署训练好的神经网络不只是把算子翻译成 GPU kernel，而是涉及图 IR 变换、融合、实现选择、内存放置和量化等相互依赖决策的编译问题，即调度。本文为系列第一部分，介绍相关挑战。
AI推荐理由 NVIDIA 官方博客，将 TensorRT 引擎构建描述为涉及图变换、融合、实现选择、内存布局和量化的调度编译问题，对理解推理部署有参考价值；但正文片段仅给出问题背景，未提供具体方案细节或实测数据。
70
正文
Deploying a trained neural network involves more than translating each operator into a GPU kernel. It is a compilation problem with many legitimate answers. For...
Deploying a trained neural network involves more than translating each operator into a GPU kernel. It is a compilation problem with many legitimate answers. For example, when NVIDIA TensorRT builds an engine, it makes interdependent decisions about graph-IR transformations, fusion, implementation selection, memory placement, and quantization. This process is called scheduling.
Source