-
The doc Gst-nvinfer — DeepStream 6.3 Release documentation (nvidia.com) describe that dla just support Nvidia Jetson AGX Xavier.
-
Does Deepstream have a plan to support DLA in Jetson AGX ORIN? If so, can you provide a specific version and time?
-
Can I directly export an engine file that supports DLA on the Jetson platform through Tensortrt, and then load this file through Deepstream?
-
Is it possible to support DLA on Deepstream and Jetson AGX ORIN platform by myself. If possible, please provide me with detailed guidance.
Hi,
1./2.
DLA can also work on Orin except for Orin Nano.
We will check with the Deepstream team to update the document.
3. Yes, please use model-engine-file
flag.
model-engine-file=model_b1_fp32.engine
4. It’s supported. Please give it a try directly.
Thanks.
Hi,
Just for your reference:
We have updated the document:
Thanks
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.