Hi, I am trying to run TensorRT-llm on AGX thor, which setup guide should I follow, and which docker image from the NGC?
Hi,
For Thor, the variant is TensorRT Edge LLM, which is not ready yet.
It’s expected to be available with our next JetPack release in early next year.
Thanks.
Thanks for the update, so what can I use in the meanwhile?
Hi,
You can find vLLM and SGLang from our NGC link below:
Thanks.
I also want to optimize the models, will this container support that, I want to perform PTQ.
Hi,
Do you use an LLM model?
If not, you can use TensorRT directly.
For LLM, you can find some benchmark data with vLLM in the topic below:
Thanks.