What is the best practice on Jetson Orin Agx? #264
Description
Hi~I wonder which method is the best for NVILA deployment on Jetson Orin Agx (TinyChat \ TensorRT LLM \ Dynamo)? For the consideration of inference speed, memory cost, etc.
{{ message }}
Hi~I wonder which method is the best for NVILA deployment on Jetson Orin Agx (TinyChat \ TensorRT LLM \ Dynamo)? For the consideration of inference speed, memory cost, etc.