[None][test] Remove duplicate test cases in llm_perf_core file

[yufeiwu-nv]

Signed-off-by: yufeiwu-nv 230315618+yufeiwu-nv@users.noreply.github.com

Summary by CodeRabbit

• Tests
  • Expanded performance test coverage with new model configurations for streaming and throughput scenarios.
  • Enhanced speculative decoding support in performance benchmarking.
  • Added new model variants to performance test matrix across multiple GPU tiers.
  • Improved remote code trust handling for newly supported models.

Description

Also add nemotron_3_super_120b_nvfp4 serve test cases

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.

[coderabbitai]

📝 Walkthrough

Walkthrough

The PR updates performance testing infrastructure for the TensorRT-LLM framework by splitting nemotron model configurations into streaming and throughput variants, updating the perf test harness to handle spec-decoding models correctly, and expanding the performance test matrix with new models and GPU tier constraints across multiple hardware configurations.

Changes

Performance Configuration and Testing

Layer / File(s)	Summary
Model streaming and throughput configuration split tests/integration/defs/perf/pytorch_model_config.py	Splits nemotron_3_super_120b_nvfp4 and nemotron_3_super_120b_nvfp4_mtp into streaming/serve patterns with enable_attention_dp=False and smaller batch size (8), and throughput patterns with enable_attention_dp=True and larger batch size (256), with MTP variant supporting speculative decoding in throughput mode.
Serve client and model trust configuration tests/integration/defs/perf/test_perf.py	Adds nemotron_nano_12b_v2, phi_4_multimodal_instruct and variants to TRUST_REMOTE_CODE_MODELS, introduces SPEC_DEC_MODELS constant aggregating spec-decoding models, and updates serve-client command construction to conditionally append --ignore-eos only for non-spec-decoding models.
Performance test matrix GPU tier updates tests/integration/test_lists/qa/llm_perf_core.yml	Reorganizes the LLM performance test matrix with updated GPU tier headers, adjusted compute capability constraints, expanded model coverage (qwen3.5 variants, llama_v3.3 configs, deepseek_r1), increased system GPU count requirements for RTX-6000D/Server tier, and new nemotron_3_super_120b_nvfp4 serve-based test entries across multiple GPU tiers.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14570: Both PRs modify tests/integration/defs/perf/test_perf.py to expand TRUST_REMOTE_CODE_MODELS for nemotron_nano_12b_v2 and phi_4_multimodal_instruct (FP4/FP8), aligning the perf harness' trust_remote behavior for these new models.

Suggested reviewers

• StanleySun639
• LarryXFly
• ruodil
• niukuo

🚥 Pre-merge checks | ✅ 2 | ❌ 3

❌ Failed checks (3 warnings)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The title describes removing duplicate test cases in llm_perf_core, but the raw summary shows the changes actually add new test cases, update configurations, and reorganize GPU test groupings rather than simply removing duplicates.	Update the PR title to accurately reflect that the changes reorganize GPU test groupings and add new model/perf test cases (like qwen3.5 variants and nemotron_3_super_120b_nvfp4-serve) in addition to removing old ones.
Description check	⚠️ Warning	The PR description is mostly empty placeholders from the template. The author checked the final PR Checklist box but provided no actual description content, test coverage explanation, or narrative justification for the changes.	Fill in the Description section explaining what duplicate test cases were removed and why, and provide specific Test Coverage details for the changes made to pytorch_model_config.py, test_perf.py, and llm_perf_core.yml.
Docstring Coverage	⚠️ Warning	Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
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.}

[coderabbitai]

Actionable comments posted: 3

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/integration/defs/perf/pytorch_model_config.py`:
- Around line 517-568: The throughput entries' pattern strings
('nemotron_3_super_120b_nvfp4-' and 'nemotron_3_super_120b_nvfp4_mtp') are too
broad and accidentally match streaming/low-latency labels, causing their
'config' (e.g., enable_attention_dp, cuda_graph_config.max_batch_size) to
override streaming variants; fix by making the patterns non-overlapping (for
example rename to a distinct suffix like
'nemotron_3_super_120b_nvfp4_throughput' and
'nemotron_3_super_120b_nvfp4_mtp_throughput' or use more specific anchors) so
the throughput entries in the 'patterns' lists no longer match streaming serve
labels and won't overwrite the streaming configs.

In `@tests/integration/test_lists/qa/llm_perf_core.yml`:
- Line 414: The list entry
"perf/test_perf.py::test_perf[deepseek_r1_0528_fp4-bench-pytorch-streaming-float4-maxbs:512-maxnt:5220-input_output_len:4000,2000-reqs:512-ep:8-tp:8-gpus:8]`#max_throughput`"
is malformed because the trailing "`#max_throughput`" is being treated as part of
the scalar; fix it by separating the comment from the scalar (e.g., add a space
before the #) or by quoting the entire test id string so the "#" is preserved
correctly as a comment marker or literal, updating the entry in
tests/integration/test_lists/qa/llm_perf_core.yml where that test id appears.
- Around line 251-254: The QA perf entries for
nemotron_3_super_120b_nvfp4-serve-pytorch-float4 (and the other missing QA cases
qwen3.5_9b, qwen3.5_27b, qwen3.5_122b_a10b,
deepseek_r1_0528_fp4-bench-pytorch-streaming-float4) that appear in
tests/integration/test_lists/qa/llm_perf_core.yml are not present in the
authoritative CI test-db files under
tests/integration/test_lists/test-db/l0_perf*.yml; add equivalent entries to
those l0_perf*.yml files so the CI DB includes the perf cases referenced (e.g.,
perf/test_perf.py::test_perf[nemotron_3_super_120b_nvfp4-serve-pytorch-float4-...],
perf/test_perf.py::test_perf[qwen3.5_9b-...],
perf/test_perf.py::test_perf[qwen3.5_27b-...],
perf/test_perf.py::test_perf[qwen3.5_122b_a10b-...], and
perf/test_perf.py::test_perf[deepseek_r1_0528_fp4-bench-pytorch-streaming-float4-...])
ensuring the exact test identifiers, markers (min_latency / max_throughput) and
parameter strings are copied so CI will discover and run the same cases.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: da3dc35b-eff7-4168-87e5-b47b897eff22

📥 Commits

Reviewing files that changed from the base of the PR and between c7683f2 and e944483.

📒 Files selected for processing (3)

• tests/integration/defs/perf/pytorch_model_config.py
• tests/integration/defs/perf/test_perf.py
• tests/integration/test_lists/qa/llm_perf_core.yml

[yufeiwu-nv]

Pushed af4dd69 fixing the two valid CodeRabbit issues (nemotron pattern overlap + missing space before #max_throughput). The third thread (CI test-db vs QA list) is out of scope and was resolved with explanation.

/bot run

[yufeiwu-nv]

/bot

[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.

[yufeiwu-nv]

/bot skip --comment "only test cases modify"

[tensorrt-cicd]

PR_Github #51535 [ skip ] triggered by Bot. Commit: 97de773 Link to invocation

[tensorrt-cicd]

PR_Github #51535 [ skip ] completed with state SUCCESS. Commit: 97de773
Skipping testing for commit 97de773

Link to invocation

[yufeiwu-nv]

/bot skip --comment "only test cases modify"

[tensorrt-cicd]

PR_Github #51761 [ skip ] triggered by Bot. Commit: dc708b7 Link to invocation

[tensorrt-cicd]

PR_Github #51761 [ skip ] completed with state SUCCESS. Commit: dc708b7
Skipping testing for commit dc708b7

Link to invocation