[https://nvbugs/6506920][fix] Recover DSpark E2E coverage

[longlee0622]

Dev Engineer Review

• Lowered the DeepSeek-V4-Pro DSpark GSM8K accuracy floor from 96.0 to 95.9.
• Updated the related comment to match the new floor.
• Removed the obsolete skip entry for test_gsm8k_dep8_megamoe_deepgemm.
• The changes have limited scope.
• No implementation or API changes are included.

QA Engineer Review

• Removed the test waiver from tests/integration/test_lists/waives.txt.
• No test-db/ or qa/ files were modified.
• CBTS coverage data is unavailable.

Verdict: needs follow-up

Description

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]

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: 68776765-43b1-421f-8a9c-b5fc7ddcb889

📥 Commits

Reviewing files that changed from the base of the PR and between 7e0c418 and 483ebb9.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

🚧 Files skipped from review as they are similar to previous changes (1)

• tests/integration/test_lists/waives.txt

---

Walkthrough

The DeepSeek-V4-Pro DSpark GSM8K accuracy floor changed from 96.0 to 95.9. The related integration test waiver was removed.

Changes

DeepSeek GSM8K validation

Layer / File(s)	Summary
Update GSM8K threshold and waiver tests/integration/defs/accuracy/references/gsm8k.yaml, tests/integration/test_lists/waives.txt	The accuracy floor changed to 95.9, and the corresponding GSM8K test skip entry was removed.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#17217: Removes a different DeepSeek test waiver from the same waiver list.
• NVIDIA/TensorRT-LLM#17301: Removes a GSM8K-related skip entry for a different DeepSeek test.

Suggested reviewers: qijune, yuanjingx87, larryxfly

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description leaves the required Description and Test Coverage sections empty and provides no implementation or test details.	Add a concise issue and solution summary, list the relevant tests, and complete the checklist based on the changes.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the NVBugs fix and the recovery of DSpark E2E coverage.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[longlee0622]

/bot run --disbale-fail-fast

[tensorrt-cicd]

PR_Github #64024 Bot args parsing error: usage: /bot [-h]
{run,kill,skip,submit,reviewers,reuse-pipeline,reuse-review} ...
/bot: error: unrecognized arguments: --disbale-fail-fast

Link to invocation

[longlee0622]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64028 [ run ] triggered by Bot. Commit: 62eb5c3 Link to invocation

[tensorrt-cicd]

PR_Github #64028 [ run ] completed with state SUCCESS. Commit: 62eb5c3
/LLM/main/L0_MergeRequest_PR pipeline #51958 completed with status: 'FAILURE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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

[tburt-nv]

I mostly see driver/hardware issues in the test history, and only one accuracy-related failure. Somehow I don't see the same issue on other tests at the same time, so I wonder if this test exercises the driver in a unique way. We should keep an eye on this test after unwaiving it for a while in case that intermittent driver issue is still present.

[longlee0622]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64212 [ run ] triggered by Bot. Commit: 62eb5c3 Link to invocation

[coderabbitai]

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

[longlee0622]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64212 [ run ] completed with state FAILURE. Commit: 62eb5c3
/LLM/main/L0_MergeRequest_PR pipeline #52124 completed with status: 'FAILURE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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

[tensorrt-cicd]

PR_Github #64280 [ run ] triggered by Bot. Commit: 7e0c418 Link to invocation

[longlee0622]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64326 [ run ] triggered by Bot. Commit: 483ebb9 Link to invocation

[tensorrt-cicd]

PR_Github #64280 [ run ] completed with state ABORTED. Commit: 7e0c418

Link to invocation

[tensorrt-cicd]

PR_Github #64326 [ run ] completed with state FAILURE. Commit: 483ebb9
/LLM/main/L0_MergeRequest_PR pipeline #52222 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

[longlee0622]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64340 [ run ] triggered by Bot. Commit: 483ebb9 Link to invocation