mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-05 18:51:38 +08:00
9f0f52249e
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
8 lines
431 B
Markdown
8 lines
431 B
Markdown
# 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:
|
|
|
|
1. Creating TensorRT plugin manually, you can refer to [manual plugin example](./manual_plugin/) for details,
|
|
2. Generate the TensorRT plugins automatically, please refer to [automatic plugin example](./plugin_autogen/) for details.
|