让长时间运行的 NVIDIA TensorRT 引擎构建在 Python 或 C++ 中可观测、可取消
Make Long-Running NVIDIA TensorRT Engine Builds Observable and Cancelable in Python or C++
NVIDIA 提出让长时间运行的 TensorRT 引擎构建在 Python 或 C++ 中变得可观测、可取消，以解决构建过程无进度反馈的问题。TensorRT 引擎构建可能耗时数秒到数分钟，大型强类型模型、深层 tactic 搜索以及全新 GPU SKU 上的冷 timing cache 都会拉长构建时间。
A TensorRT engine build can take seconds to many minutes. Large strongly typed models, deep tactic search, and a cold timing cache on a brand-new GPU SKU can...
A TensorRT engine build can take seconds to many minutes. Large strongly typed models, deep tactic search, and a cold timing cache on a brand-new GPU SKU can leave developers, end users, or AI agents staring at a frozen terminal with no idea whether to wait, retry, or kill the process. Most NVIDIA TensorRT integrations report nothing during a build or provide no way to abort early.
来源：NVIDIA Developer Blog · developer.nvidia.com