mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
| .. | ||
| manual_plugin | ||
| plugin_autogen | ||
| README.md | ||
Integration for OpenAI Triton
The typical approach to integrate a kernel into TensorRT-LLM is to create TensorRT plugins. Specially for integrating OpenAI Triton kernels, there are two methods:
- Creating TensorRT plugin manually, you can refer to manual plugin example for details,
- Generate the TensorRT plugins automatically, please refer to automatic plugin example for details.