Jetson-storage error?

[wlskaka4]

Visual Language Models (VLM) with Jetson Platform Services — Jetson Platform Services documentation

Storage — Jetson Platform Services documentation

When I run docker compose up without connecting jetson-storage to nvme0n1, the directory /data/genai-volume/models/ is created, and the VLM model is downloaded. However, when I connect jetson-storage and run docker compose up, the directory /data/genai-volume/models/ is not created, and the VLM model is not downloaded. I want to connect jetson-storage and download the model. How can I achieve this?

platform: Jetson Orin AGX AVermedia D315, Jetpack 6.1

[carolyuu]

Hi,
Here are some suggestions for the common issues:

1. Performance

Please run the below command before benchmarking deep learning use case:

$ sudo nvpmodel -m 0
$ sudo jetson_clocks

2. Installation

Installation guide of deep learning frameworks on Jetson:

• TensorFlow: Installing TensorFlow for Jetson Platform - NVIDIA Docs
• PyTorch: Installing PyTorch for Jetson Platform - NVIDIA Docs
  We also have containers that have frameworks preinstalled:
  Data Science, Machine Learning, AI, HPC Containers | NVIDIA NGC

3. Tutorial

Startup deep learning tutorial:

• Jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson
• TensorRT sample: Jetson/L4T/TRT Customized Example - eLinux.org

4. Report issue

If these suggestions don’t help and you want to report an issue to us, please attach the model, command/step, and the customized app (if any) with us to reproduce locally.

Thanks!

[wlskaka4]

I had already done them all.

[kesong]

Can you have a try with below command line before run docker compose up
$ sudo chmod -R 777 /data/genai-volume/

[wlskaka4]

I change docker data-root to /mnt/nvme/docker

It’s done