home/categories/framework-internals/amd-agi-apex-tools-skills-pytorch-kernel-optimization-skill-md
framework-internalsdevelopment

pytorch-kernel-optimization

This skill should be used when optimizing PyTorch models and kernels, including efficient tensor operations, torch.compile, custom autograd/CUDA/Triton extensions, mixed precision, memory and data pipeline tuning, model optimization techniques, CUDA graphs, and profiling.

AMD-AGI
maintainer
AMD-AGI
更新于 3/23/2026
星标
60
分支
8
quick start

Installation and usage

This skill should be used when optimizing PyTorch models and kernels, including efficient tensor operations, torch.compile, custom autograd/CUDA/Triton extensions, mixed precision, memory and data pipeline tuning, model optimization techniques, CUDA graphs, and profiling.

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 pytorch-kernel-optimization