Upgrade the TensorRT container version

[ajrasane]

What does this PR do?

Type of change: Container version update

• Upgraded the TensorRT container version to 26.02
• This supports TensorRT 10.15.1

Testing

Unit and integrations tests pass

Before your PR is "Ready for review"

Make sure you read and follow Contributor guidelines and your commits are signed (git commit -s -S).

Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded trust_remote_code=True, torch.load(..., weights_only=False), pickle, etc.).

• Is this change backward compatible?: ✅ / ❌ / N/A
• If you copied code from any other sources or added a new PIP dependency, did you follow guidance in CONTRIBUTING.md: ✅ / ❌ / N/A
• Did you write any new necessary tests?: ✅ / ❌ / N/A
• Did you update Changelog?: ✅ / ❌ / N/A

Summary by CodeRabbit

• Documentation

  • Updated example guides to reference the latest TensorRT Docker image version (26.02)
  • Added compatibility note for onnxruntime-gpu usage

• Chores

  • Updated CI/CD workflows to use the latest TensorRT Docker image version

[coderabbitai]

📝 Walkthrough

Walkthrough

This pull request updates TensorRT Docker image versions across CI/CD configuration and example documentation. The workflow configuration updates from version 26.01 to 26.02, while example docs update from 25.08 to 26.02. One documentation addition includes a note on CUDA 12 compatibility for onnxruntime-gpu.

Changes

Cohort / File(s)	Summary
Workflow Configuration .github/workflows/example_tests.yml	Updated TensorRT Docker image tag from 26.01-py3 to 26.02-py3 in onnx-pr and onnx-non-pr test jobs.
Example Documentation examples/diffusers/README.md, examples/onnx_ptq/README.md, examples/torch_onnx/README.md	Updated TensorRT Docker image tag from 25.08-py3 to 26.02-py3. Added CUDA 12 compatibility note in onnx_ptq recommending 25.06-py3 for onnxruntime-gpu package.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 4

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'Upgrade the TensorRT container version' directly and clearly summarizes the main change: updating TensorRT Docker image tags across workflow files and documentation from older versions (25.08 or 26.01) to 26.02.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Security Anti-Patterns	✅ Passed	Pull request contains only non-Python changes (Docker image version updates in YAML and Markdown documentation). No Python code anti-patterns are present.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch ajrasane/tensorrt_upgrade

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

🧹 Nitpick comments (1)

examples/onnx_ptq/README.md (1)

25-27: Document specific onnxruntime-gpu versions tested with each TensorRT container tag.

The note recommends 25.06-py3 for onnxruntime-gpu compatibility, but the reasoning is unclear. Latest stable onnxruntime-gpu (v1.24.4) requires CUDA 12.x, and the recommended 26.02-py3 container includes CUDA 13.1.1, which maintains forward compatibility with CUDA 12.x applications. Rather than suggesting version downgrades, explicitly list which onnxruntime-gpu versions (or version ranges) have been tested with each recommended container tag to avoid drift and provide clear guidance.

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@examples/onnx_ptq/README.md` around lines 25 - 27, Update the README note to
specify which onnxruntime-gpu versions were tested with each TensorRT container
tag: explicitly list tested versions or version ranges for
nvcr.io/nvidia/tensorrt:26.02-py3 and nvcr.io/nvidia/tensorrt:25.06-py3 and
reference the package name onnxruntime-gpu (e.g., tested v1.24.x, v1.25.x, etc.
as applicable); mention the CUDA compatibility rationale (CUDA 13.1.1 in 26.02
is forward-compatible with CUDA 12.x apps) so readers aren’t advised to
downgrade, and add a short “Tested with” line or table near the existing
recommendation for clarity.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Nitpick comments:
In `@examples/onnx_ptq/README.md`:
- Around line 25-27: Update the README note to specify which onnxruntime-gpu
versions were tested with each TensorRT container tag: explicitly list tested
versions or version ranges for nvcr.io/nvidia/tensorrt:26.02-py3 and
nvcr.io/nvidia/tensorrt:25.06-py3 and reference the package name onnxruntime-gpu
(e.g., tested v1.24.x, v1.25.x, etc. as applicable); mention the CUDA
compatibility rationale (CUDA 13.1.1 in 26.02 is forward-compatible with CUDA
12.x apps) so readers aren’t advised to downgrade, and add a short “Tested with”
line or table near the existing recommendation for clarity.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 86d9cb9d-874d-449b-9881-e3f1c39e7135

📥 Commits

Reviewing files that changed from the base of the PR and between 714dbd2 and 51bd864.

📒 Files selected for processing (4)

• .github/workflows/example_tests.yml
• examples/diffusers/README.md
• examples/onnx_ptq/README.md
• examples/torch_onnx/README.md

[github-actions]

PR Preview Action v1.8.1
Preview removed because the pull request was closed.
2026-03-24 22:31 UTC

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 70.18%. Comparing base (d0bf0be) to head (51bd864).
⚠️ Report is 5 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1112      +/-   ##
==========================================
- Coverage   70.23%   70.18%   -0.06%     
==========================================
  Files         227      228       +1     
  Lines       25909    25952      +43     
==========================================
+ Hits        18198    18214      +16     
- Misses       7711     7738      +27     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.