Fix JetPack 6.2 Dockerfile: Build ONNX Runtime from source with ARM64-compatible headers #1623
+140
−56
Conversation
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
alexnorell
force-pushed
the
jetpack-6.2-onnx-runtime-fix
branch
from
ee41f13 to
b9b3957
Compare
- Compile ONNX Runtime v1.23.1 from source for ARM64 compatibility - Update CMake to v4.1.2 - Remove x86-specific CCCL headers (use Jetson's native CUDA headers) - Fix PyPI URL to https://pypi.jetson-ai-lab.io/jp6/cu126 - Add TensorRT and CUDA execution provider support - Use uv for faster package installation - Multi-stage build for optimized image size
alexnorell
force-pushed
the
jetpack-6.2-onnx-runtime-fix
branch
from
b9b3957 to
9acad27
Compare
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Outdated suggestions cannot be applied.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.
Description
Fixes critical issues with the JetPack 6.2 (CUDA 12.6) Dockerfile by compiling ONNX Runtime v1.23.1 from source instead of using pre-built packages that cause memory allocation errors.
Type of change
How has this change been tested, please provide a testcase or example of how you tested the change?
Built and tested on Jetson AGX Orin (JetPack 6.2, CUDA 12.6):
Any specific deployment considerations
Docs