Fang Shao Yu

Thank you for your response! I’d like to follow up and ask — is there any recommended approach for building a TensorRT engine for Qwen2-VL-2B-Instruct directly on a Jetson Orin...

Got it, I’ll try running Qwen2-VL with the PyTorch workflow on the Jetson Orin Nano Super and see how it performs. Really appreciate your help!

@juney-nvidia That's great to hear! It's really nice to see support for the latest models coming so quickly. Qwen is truly an impressive VLM series. @sunnyqgg Understood, thank you. For...

Hi @xiaohuihuige , Have you tried using a VPN? or maybe I can share the Docker image with you. However, I'm not quite sure what's the best way to transfer...

Hi @garvitpathak, I didn’t install the latest version of TensorRT-LLM directly on the Jetson Orin Nano. Instead, I used the ARM64 image provided by Trystan on Docker Hub (https://hub.docker.com/r/trystan/tensorrt_llm/tags). You...

Hi @garvitpathak, The official team has released an INT4 version of the model using GPTQ on Hugging Face (https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4), but I haven’t personally tried this model yet. BTW, I’ve successfully...