nvidia-deepstream: Jetson AGX Thor support on DeepStream 9.1 - #27
Merged
Merged
Conversation
- avocado.yaml: add jetson-agx-thor to supported_targets; bump distro to release 2026 / channel next; move runtime to deepstream-9.1 (+ pyds) - engines-compile.sh / engines-install.sh: missing prebuilt engines now warn instead of hard-failing, so new hardware can build an image, provision, and build engines on-device, then commit them and redeploy - README / getting_started / models-compile / config / app / preflight: update 7.1 → 9.1 references
Avocado References — Build Check
Totals: 0 ✅ passed · 1 ❌ failed Per-reference logs: workflow run |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Brings the NVIDIA DeepStream reference up to DeepStream 9.1 and adds Jetson AGX Thor as a supported target.
Changes
Target + runtime
jetson-agx-thortosupported_targetsdeepstream-7.1→deepstream-9.1(+ pyds)tensorrt-trtexec-prebuiltso engines can be built on-device during bring-uptegra-libraries-pva— the NvDCF tracker's VPI feature extractor loadslibnvpvaumd_core.soat runtime (not a transitive dep of deepstream); missing on JetPack 7.2DeepStream 9.1 fixes
nvstreammux: setUSE_NEW_NVSTREAMMUX=yesand drop the legacywidth/height/batched-push-timeout/live-sourcemux properties (unsupported/ignored by the new muxer)Engines
engines-compile.sh/engines-install.sh: missing prebuilt engines now warn instead of hard-failing, so new hardware can build an image, provision, build engines on-device, then commit them and redeploy