[None][test] Update DGX spark CI/QA tests

[pamelap-nvidia]

Summary by CodeRabbit

• Tests
  • Updated integration test configurations to include new model variants for validation, including Llama 3.3 70B, DeepSeek-R1 distill Qwen 32B, Qwen3, and Nemotron Nano 9B
  • Refined and optimized single-GPU and multi-GPU test matrix selections
  • Enhanced test coverage for both performance and functional validation across the supported model portfolio

Description

Moved some functional tests from QA to CI.
Removed some perf tests in QA.

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)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• 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

To see a list of available CI bot commands, please comment /bot help.

[pamelap-nvidia]

/bot help

[github-actions]

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) --high-priority]

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. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". 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. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge".

--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.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

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.

[pamelap-nvidia]

/bot run --stage-list "GB10-PyTorch-1,GB10-PyTorch-Post-Merge-1"

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 0fa074c2-8d5d-4b96-a7b3-098941331167

📥 Commits

Reviewing files that changed from the base of the PR and between a50b5e2 and 77b5ed6.

📒 Files selected for processing (3)

• tests/integration/test_lists/qa/llm_spark_func.yml
• tests/integration/test_lists/qa/llm_spark_perf.yml
• tests/integration/test_lists/test-db/l0_gb10.yml

💤 Files with no reviewable changes (2)

• tests/integration/test_lists/qa/llm_spark_perf.yml
• tests/integration/test_lists/qa/llm_spark_func.yml

---

📝 Walkthrough

Walkthrough

This PR updates integration test-matrix configurations across three YAML files to adjust single-GPU and selective test coverage. Specific LLM model/precision variants are removed and replaced in Spark function and perf test lists, while GB10 test selections are extended with new test entries and variant combinations.

Changes

Test Matrix Configuration Updates

Layer / File(s)	Summary
Spark function single-GPU test matrix tests/integration/test_lists/qa/llm_spark_func.yml	Single-GPU test block updated: removed GPT-OSS 20B/120B and Llama 3.1 8B quickstart entries, replaced Qwen3 30B A3B and Phi-4 reasoning-plus variants with Llama 3.3 70B (FP8/FP4), Llama-4 Scout 17B FP4, DeepSeek-R1 distill Qwen 32B, Nemotron Nano 9B v2 NVFP4, and GPT-OSS-120B Eagle3 variants; accuracy and examples/serve test entries removed from this region.
Spark perf single-GPU test list tests/integration/test_lists/qa/llm_spark_perf.yml	Single-GPU perf test block updated: deprecated model/precision entries replaced with three new entries for Qwen3 32B FP4, Qwen3 32B bfloat16, and DeepSeek-R1 distill Qwen 32B bfloat16.
GB10 test-db selections tests/integration/test_lists/test-db/l0_gb10.yml	Post-merge test list: BERT quickstart and Qwen3 8B accuracy entries removed; new PyTorch accuracy, examples/serve test parametrizations, and test_ptp_quickstart_advanced variant added. Pre-merge test list: new Qwen3 30B A3B/NVFP4, Llama 3.1 8B bf16/FP8/FP4 quickstart variants, and expanded Nemotron 3 examples/serve test coverage (super 120b NVFP4, nano omni NVFP4 with text reasoning, image, and video) added.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14896: Adds CI test-matrix selections for Llama 3.3 70B FP4/FP8 variants, which align with the newly added Llama 3.3 model entries in this PR's single-GPU test matrix.
• NVIDIA/TensorRT-LLM#14660: Updates the same integration test-selection YAMLs by removing and replacing test_ptp_quickstart_advanced and perf test entries, demonstrating consistent model coverage adjustment patterns.
• NVIDIA/TensorRT-LLM#14854: Updates single-GPU Spark test matrix to adjust guided-decoding e2e test cases, overlapping with the test-selection configuration changes in this PR.

Suggested reviewers

• litaotju
• niukuo
• StanleySun639

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The description section is minimally filled with only two brief sentences; critical details like rationale, test migration reasoning, and affected test cases are missing.	Expand the description to include why tests were moved from QA to CI, which specific tests were removed/added, and the impact on test coverage.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the main change: updating DGX Spark CI/QA tests across multiple test configuration files.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #52178 [ run ] triggered by Bot. Commit: 77b5ed6 Link to invocation

[tensorrt-cicd]

PR_Github #52178 [ run ] completed with state ABORTED. Commit: 77b5ed6
/LLM/main/L0_MergeRequest_PR pipeline #41499 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation