JetPack 4.6 Production Release with L4T 32.6.1

We are pleased to announce JetPack 4.6, a production release supporting Jetson AGX Xavier series, Jetson Xavier NX, Jetson TX2 series, Jetson TX1, and Jetson Nano.

JetPack 4.6 includes support for Triton Inference Server, new versions of CUDA, cuDNN and TensorRT, VPI 1.1 with support for new computer vision algorithms and python bindings, L4T 32.6.1 with Over-The-Air update features, security features, and a new flashing tool to flash internal or external media connected to Jetson.

In addition to l4t-base container image, new CUDA runtime and TensorRT runtime container images are released on NVIDIA NGC, which include CUDA and TensorRT runtime components inside the container itself, as opposed to mounting those components from the host. These containers are built to containerize AI applications for deployment. Note that the L4T-base container continues to support existing containerized applications that expect it to mount CUDA and TensorRT components from the host.

Highlights of JetPack 4.6 are:

  • Support for Jetson AGX Xavier Industrial module.
  • Support for new 20W mode on Jetson Xavier NX enabling better video encode and video decode performance and higher memory bandwidth. The included 10W and 15W nvpmodel configurations will perform exactly as did the 10W and 20W modes with previous JetPack releases. Any custom nvpmodel created with a previous release will require regeneration for use with JetPack 4.6. Please read release notes for details.
  • Image based Over-The-Air update tools for developing end-to-end OTA solution for Jetson products in the field. Supported on Jetson TX2 series, Jetson Xavier NX and Jetson AGX Xavier series. Download the OTA tools from the L4T page under the Tools section.
  • A/B Root File System redundancy to flash, maintain and update redundant root file systems. Enhances fault tolerance during OTA by falling back to the working root file system slot in case of a failure. Supported on Jetson TX2 series, Jetson Xavier NX and Jetson AGX Xavier series.
  • A new flashing tool to flash internal or external media connected to Jetson1. Supports Jetson TX2 series, Jetson Xavier NX and Jetson AGX Xavier. The new tool uses initial RAM disk for flashing and is up to1.5x faster when flashing compared to the previous method2.
  • Secure boot is enhanced3 for Jetson TX2 series to extend encryption support to kernel, kernel-dtb and initrd.
  • Disk encryption of external media supported to protect data at rest for Jetson AGX Xavier series, Jetson Xavier NX and Jetson TX2.
  • NVMe driver added to CBoot for Jetson Xavier NX and Jetson AGX Xavier series. Enables loading kernel, kernel-dtb and initrd from the root file system on NVMe.
  • Enhanced Jetson-IO tools to configure the camera header interface and dynamically add support for a camera using device tree overlays
  • Support for Scalable Video Coding (SVC) H.264 encoding
  • Support for YUV444 8, 10 bit encoding and decoding
  • Direct downloadable links to JetPack and L4T debian packages for Jetson

Visit JetPack 4.6 and L4T 32.6.1 page for more details.

JetPack 4.6 components:

  • L4T R32.6.1
  • CUDA 10.2
  • cuDNN 8.2.1
  • TensorRT 8.0.1
  • VisionWorks 1.6
  • OpenCV 4.1.1
  • Vulkan 1.2
  • VPI 1.1
  • Nsight Systems 2021.2
  • Nsight Graphics 2021.2
  • Nsight Compute 2019.3

Install JetPack 4.6 using SDK Manager or SD card image (for Jetson Nano 2GB Developer Kit, Jetson Nano Developer Kit and Jetson Xavier NX Developer Kit) or upgrade via Debian package management tool (refer to the instructions here)

Refer to Jetson Roadmap page for roadmap on Jetson hardware and software.

Please register to following webinars:

[1] Flashing from NFS is deprecated and replaced by the new flashing tool which uses initrd

Wonderful some function updates! 🎉

I have a easy question. Do you have a plan that set git-tag like tegra-l4t-r32.6.1 in some kernel repositories?

https://nv-tegra.nvidia.com/gitweb/?p=linux-4.9.git;a=summary

@naoki.matt.matsumoto the git-tag for 32.6.1 is present now.
https://nv-tegra.nvidia.com/gitweb/?p=linux-4.9.git;a=summary

@suhash -san

Thank you. I confirmed all kernel repositories was published!


One more other topics. I’ve found a easy bugs.

The define tables of source_sync.sh has a easy wrong about new repository galen-industrial-dts.git by cut and paste.

k:hardware/nvidia/platform/t19x/mccoy/kernel-dts:nv-tegra.nvidia.com/device/hardware/nvidia/platform/t19x/mccoy-dts.git:
k:hardware/nvidia/platform/t19x/mccoy/kernel-dts:nv-tegra.nvidia.com/device/hardware/nvidia/platform/t19x/galen-industrial-dts.git:

so can the jetson finally boot from nvme ssd without eMMC at all?
can the OS be flashed to nvme directly by flashing tool? if yes, which exactly flashing will do?
Thanks

@Andrey1984

Jetson Xavier NX as QSPI and boots from it and hence with the NVME driver in the bootloader, we can now only flash QSPI and NVME and load from NVME without touching emmc at all.
But things are different on Jetson AGX Xavier where there is no QSPI and boots from emmc. So we need to have minimum thing flashe to emmc, so that bootloader running from emmc can then load the rootfs, kernel, dtb, etc from NVME.
Please use the new flashing tool for this, refer to “Flashing using initrd” section of the documentation (also there is a README in the BSP which has many examples) https://docs.nvidia.com/jetson/archives/l4t-archived/l4t-3261/index.html#page/Tegra%20Linux%20Driver%20Package%20Development%20Guide/flashing.html#wwpID0E0PI0HA

Also i announce to you and the forum that we will be releasing support for flashing external media like NVME/USB connected to Jetson Xavier NX or Jetson AGX Xavier from SDKM itself soon!

1 Like

Triton Inference Server release supporting JetPack 4.6 is live now!

Visit server/jetson.md at main · triton-inference-server/server · GitHub

JetPack 4.6 containers are live now on NGC!
As mentioned in the announcement, we have release 2 new containers this time, a cuda runtime container and a tensorrt runtime container. These containers include CUDA and TensorRT runtime components inside the container itself, as opposed to mounting those components from the host.

L4T base container: NVIDIA NGC
CUDA Runtime Container: NVIDIA NGC
Tensorrt Runtime Container: NVIDIA NGC

According to the documentation of the link you shared, we need to download secureboot package for using the feature, but I found the secureboot package only for 32.3.1 and older and cannot found it for the latest L4T version (32.6.1).
Could you clarify the procedure to use the new flashing tool by showing the actual pages, paragraphs or resources which are required for it, please?

I found the link for the package:
https://developer.nvidia.com/embedded/l4t/r32_release_v6.1/t186/secureboot_r32.6.1_aarch64.tbz2
which does not showed up when I input ‘secure boot’ on the download center, though.

Can JetPack 4.6 do the NVMe boot for AGX?

Please help: How AGX boot from NVMe with Jetpack 4.6