debuggingtools
perf-host-optimization
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
maintainer
NVIDIA
更新于 4/8/2026
星标
13335
分支
2271
quick start
Installation and usage
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
安装
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use perf-host-optimization