Optimize Jetson 6.2.0 Dockerfile with l4t-ml base image #1614
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
feat/cu126
branch
4 times, most recently
from
f5904db to
18a9520
Compare
Update Jetson 6.2.0 Dockerfile to use roboflow/l4t-ml:r36.4-slim base image, which includes pre-built PyTorch 2.8, ONNXRuntime with TensorRT, OpenCV with CUDA, and scientific computing packages. This removes the need for OpenCV compilation (~30+ min build time) and significantly improves build speed. Also removes JupyterLab from edge deployment requirements. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
alexnorell
force-pushed
the
feat/cu126
branch
from
18a9520 to
5bb436c
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Outdated suggestions cannot be applied.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
Update Jetson 6.2.0 Dockerfile to use
roboflow/l4t-ml:r36.4-slimbase image, which includes pre-built PyTorch 2.8, ONNXRuntime with TensorRT, OpenCV with CUDA, cupy, pycuda, and scientific computing packages (NumPy, SciPy, scikit-learn, pandas, scikit-image).Changes:
nvcr.io/nvidia/l4t-jetpack:r36.4.0withroboflow/l4t-ml:r36.4-slimrequirements.gpu.txtinstallation (ONNXRuntime already in base)Type of change
How has this change been tested, please provide a testcase or example of how you tested the change?
Local build testing on Jetson AGX Orin with L4T 36.4.4 (JetPack 6.2.1). Verified all required packages are present in base image and inference server starts successfully.
Any specific deployment considerations
The new base image (
roboflow/l4t-ml:r36.4-slim) is 12.3GB and available on Docker Hub. Build time significantly reduced by eliminating OpenCV compilation. All existing functionality preserved.Docs