[https://nvbugs/5769712][fix] fix timeout in AutoDeploy llama accuracy test (#10461)#10851

lucaslie · 2026-01-20T16:12:58Z

Summary by CodeRabbit

Tests
- Updated test configuration for model compilation backend selection.
- Adjusted test skip list entries for integration testing.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

Description

cherry-picks nvbug fix #10461 into release branch

Test Coverage

PR Checklist

Please review the following before submitting your PR:

PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

lucaslie · 2026-01-20T16:13:29Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

coderabbitai · 2026-01-20T16:15:42Z

📝 Walkthrough

Walkthrough

The PR updates the model compilation backend configuration from "torch-opt" to "torch-cudagraph" in an AutoDeploy integration test and adjusts test skip list entries to remove one skipped test entry and add another.

Changes

Cohort / File(s)	Summary
Test Configuration `tests/integration/defs/accuracy/test_llm_api_autodeploy.py`	Updated compile\_model backend from "torch-opt" to "torch-cudagraph" in TestLlama3\_1\_8B.get\_default\_kwargs
Test Skip List `tests/integration/test_lists/waives.txt`	Removed SKIP entry for test\_llm\_api\_autodeploy.py::TestLlama3\_1\_8B::test\_auto\_dtype[False-4], added SKIP entry for test\_e2e.py::test\_openai\_completions\_example[trt]

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

Possibly related PRs

PR #10461: Changes the same compile\_model backend configuration in the test\_llm\_api\_autodeploy.py file from "torch-opt" to "torch-cudagraph"

Suggested reviewers

EmmaQiaoCh
greg-kwasniewski1
venkywonka
suyoggupta

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is incomplete; it lacks details on the issue, solution, test coverage, and only contains template boilerplate.	Add a meaningful description explaining the timeout issue, the backend configuration change, and test coverage details.
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the fix addressing a timeout in the AutoDeploy LLaMA accuracy test with proper NVBug ID and type tags.
Linked Issues check	✅ Passed	The code changes fully meet linked issue `#10461` requirements: backend changed from 'torch-opt' to 'torch-cudagraph' and previously skipped test case re-enabled.
Out of Scope Changes check	✅ Passed	All changes are directly related to the linked issue: updating backend configuration and updating test skip list as specified.

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

✨ Finishing touches

📝 Generate docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

coderabbitai

Actionable comments posted: 0

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

tests/integration/defs/accuracy/test_llm_api_autodeploy.py (1)
1-2: Update NVIDIA copyright year to 2026.

This file was modified in 2026; the header should reflect the latest meaningful modification year. As per coding guidelines, please update it.
🔧 Suggested update
-# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.

lucaslie · 2026-01-20T16:58:55Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

tensorrt-cicd · 2026-01-20T17:05:44Z

PR_Github #32786 [ run ] triggered by Bot. Commit: 5c38b7f

tensorrt-cicd · 2026-01-20T18:37:06Z

PR_Github #32786 [ run ] completed with state SUCCESS. Commit: 5c38b7f
/LLM/release-1.2/L0_MergeRequest_PR pipeline #83 completed with status: 'FAILURE'

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

lucaslie · 2026-01-20T18:55:41Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

tensorrt-cicd · 2026-01-20T19:10:39Z

PR_Github #32797 [ run ] triggered by Bot. Commit: 5c38b7f

tensorrt-cicd · 2026-01-20T19:55:25Z

PR_Github #32797 [ run ] completed with state SUCCESS. Commit: 5c38b7f
/LLM/release-1.2/L0_MergeRequest_PR pipeline #89 completed with status: 'FAILURE'

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

lucaslie · 2026-01-20T21:49:16Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

tensorrt-cicd · 2026-01-20T22:01:02Z

PR_Github #32810 [ run ] triggered by Bot. Commit: 5c38b7f

tensorrt-cicd · 2026-01-20T22:59:30Z

PR_Github #32810 [ run ] completed with state SUCCESS. Commit: 5c38b7f
/LLM/release-1.2/L0_MergeRequest_PR pipeline #91 completed with status: 'FAILURE'

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

…y test (NVIDIA#10461) Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

lucaslie · 2026-01-21T14:33:27Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

tensorrt-cicd · 2026-01-21T14:39:37Z

PR_Github #32967 [ run ] triggered by Bot. Commit: 8e57c6c

tensorrt-cicd · 2026-01-21T15:51:03Z

PR_Github #32967 [ run ] completed with state SUCCESS. Commit: 8e57c6c
/LLM/release-1.2/L0_MergeRequest_PR pipeline #127 completed with status: 'FAILURE'

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

lucaslie · 2026-01-22T15:45:23Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

tensorrt-cicd · 2026-01-22T15:52:01Z

PR_Github #33195 [ run ] triggered by Bot. Commit: 8e57c6c

tensorrt-cicd · 2026-01-22T20:34:25Z

PR_Github #33195 [ run ] completed with state SUCCESS. Commit: 8e57c6c
/LLM/release-1.2/L0_MergeRequest_PR pipeline #174 completed with status: 'FAILURE'

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

lucaslie · 2026-01-22T21:27:12Z

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

tensorrt-cicd · 2026-01-22T21:33:24Z

PR_Github #33226 [ run ] triggered by Bot. Commit: 8e57c6c

tensorrt-cicd · 2026-01-22T23:05:23Z

PR_Github #33226 [ run ] completed with state SUCCESS. Commit: 8e57c6c
/LLM/release-1.2/L0_MergeRequest_PR pipeline #181 completed with status: 'SUCCESS'

…y test (NVIDIA#10461) (NVIDIA#10851) Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

…y test (NVIDIA#10461) (NVIDIA#10851) Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

lucaslie self-assigned this Jan 20, 2026

lucaslie requested a review from a team as a code owner January 20, 2026 16:12

lucaslie added this to AutoDeploy Board Jan 20, 2026

github-project-automation bot moved this to Backlog in AutoDeploy Board Jan 20, 2026

lucaslie moved this from Backlog to In review in AutoDeploy Board Jan 20, 2026

lucaslie enabled auto-merge (squash) January 20, 2026 16:13

coderabbitai bot reviewed Jan 20, 2026

View reviewed changes

syuoni approved these changes Jan 21, 2026

View reviewed changes

litaotju approved these changes Jan 21, 2026

View reviewed changes

[https://nvbugs/5769712][fix] fix timeout in AutoDeploy llama accurac…

8e57c6c

…y test (NVIDIA#10461) Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>

lucaslie force-pushed the ll/cherry-pick-10461 branch from 5c38b7f to 8e57c6c Compare January 21, 2026 14:33

lucaslie merged commit 13103af into NVIDIA:release/1.2 Jan 22, 2026
5 checks passed

github-project-automation bot moved this from In review to Done in AutoDeploy Board Jan 22, 2026

Comments

Conversation

lucaslie commented Jan 20, 2026 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

lucaslie commented Jan 20, 2026

Uh oh!

coderabbitai bot commented Jan 20, 2026

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

lucaslie commented Jan 20, 2026

Uh oh!

tensorrt-cicd commented Jan 20, 2026

Uh oh!

tensorrt-cicd commented Jan 20, 2026

Uh oh!

lucaslie commented Jan 20, 2026

Uh oh!

tensorrt-cicd commented Jan 20, 2026

Uh oh!

tensorrt-cicd commented Jan 20, 2026

Uh oh!

lucaslie commented Jan 20, 2026

Uh oh!

tensorrt-cicd commented Jan 20, 2026

Uh oh!

tensorrt-cicd commented Jan 20, 2026

Uh oh!

lucaslie commented Jan 21, 2026

Uh oh!

tensorrt-cicd commented Jan 21, 2026

Uh oh!

tensorrt-cicd commented Jan 21, 2026

Uh oh!

lucaslie commented Jan 22, 2026

Uh oh!

tensorrt-cicd commented Jan 22, 2026

Uh oh!

tensorrt-cicd commented Jan 22, 2026

Uh oh!

lucaslie commented Jan 22, 2026

Uh oh!

tensorrt-cicd commented Jan 22, 2026

Uh oh!

tensorrt-cicd commented Jan 22, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

lucaslie commented Jan 20, 2026 •

edited by coderabbitai bot

Loading