Skip to content

[None][infra] Waive 11 failed cases for main in post-merge 2757#14925

Merged
EmmaQiaoCh merged 1 commit into
NVIDIA:mainfrom
ZhanruiSunCh:trtllm-ci-report/waive-20260604-015531
Jun 4, 2026
Merged

[None][infra] Waive 11 failed cases for main in post-merge 2757#14925
EmmaQiaoCh merged 1 commit into
NVIDIA:mainfrom
ZhanruiSunCh:trtllm-ci-report/waive-20260604-015531

Conversation

@ZhanruiSunCh

@ZhanruiSunCh ZhanruiSunCh commented Jun 4, 2026

Copy link
Copy Markdown
Collaborator

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by @EmmaQiaoCh)
Target branch: main
Bug(s): 6160629, 6266259, 6266302, 6266306

Waive entries added

disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity[False-False-DeepSeek-V3-Lite-fp8/fp8] SKIP (https://nvbugs/6266302)
kv_cache/test_prefix_aware_scheduling.py::TestServePrefixAwareScheduling::test_multi_round_qa_shared_prefix_smoke SKIP (https://nvbugs/6266306)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-bf16-_tokens16-_hidden32] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-bf16-_tokens16-_hidden512] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-bf16-_tokens256-_hidden32] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-bf16-_tokens256-_hidden512] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-fp16-_tokens16-_hidden32] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-fp16-_tokens16-_hidden512] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-fp16-_tokens256-_hidden32] SKIP (https://nvbugs/6266259)
unittest/_torch/multi_gpu/test_user_buffers.py::test_user_buffers_pass[2-fp16-_tokens256-_hidden512] SKIP (https://nvbugs/6266259)
unittest/auto_deploy/standalone/test_standalone_package.py::TestStandalonePackage::test_run_unit_tests SKIP (https://nvbugs/6160629)

This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.

Summary by CodeRabbit

  • Tests
    • Updated test infrastructure to skip additional test cases for known issues or platform-specific scenarios.

Bug(s): 6160629, 6266259, 6266302, 6266306
Requested by: @EmmaQiaoCh

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
@EmmaQiaoCh

Copy link
Copy Markdown
Collaborator

/bot run

@EmmaQiaoCh
EmmaQiaoCh enabled auto-merge (squash) June 4, 2026 01:56
@coderabbitai

coderabbitai Bot commented Jun 4, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

📝 Walkthrough

Walkthrough

This PR adds test skip waiver entries to tests/integration/test_lists/waives.txt, excluding four failing test cases and their parameterized variants from CI test runs: a disaggregated LLaMA context capacity test, a KV cache prefix-aware scheduling test, eight multi-GPU user buffer test variants, and a standalone package unit test.

Changes

Test Waivers Configuration

Layer / File(s) Summary
Skip waiver entries for failing tests
tests/integration/test_lists/waives.txt
Added skip entries for test_disaggregated_llama_context_capacity, test_multi_round_qa_shared_prefix_smoke, eight test_user_buffers_pass variants across bf16/fp16 parameter sets, and test_run_unit_tests.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#14700: Main PR re-adds the waiver for test_run_unit_tests, whereas this retrieved PR removed that same waiver.
  • NVIDIA/TensorRT-LLM#14789: Both PRs modify tests/integration/test_lists/waives.txt by adding skip/waive entries for failing integration tests.
  • NVIDIA/TensorRT-LLM#14883: Both PRs modify the same waiver list file by adding skip entries for specific failing test cases and parameterizations.

Suggested reviewers

  • EmmaQiaoCh
  • chzblych
  • galagam
🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies the primary change: waiving 11 failed test cases with reference to the post-merge identifier, following the repository's required format.
Description check ✅ Passed The description provides comprehensive information including created-by details, target branch, bug references, and a detailed list of waived test entries. It meets the essential requirements despite not following all optional checklist items.
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.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🧹 Nitpick comments (1)
tests/integration/test_lists/waives.txt (1)

193-193: ⚡ Quick win

Coverage is now insufficient in the newly waived suites; add explicit unwaive follow-up tracking.

Please add a follow-up item (outside this PR is fine) for each impacted file with owner/target date to restore CI signal:

  • tests/integration/disaggregated/test_disaggregated_single_gpu.pycoverage insufficient
  • tests/integration/kv_cache/test_prefix_aware_scheduling.pycoverage insufficient
  • tests/integration/unittest/_torch/multi_gpu/test_user_buffers.pycoverage insufficient (8 parametrized cases waived)
  • tests/integration/unittest/auto_deploy/standalone/test_standalone_package.pycoverage insufficient

Given this is a waiver PR, the entries are format-correct, but these areas now need follow-up outside this PR to avoid long-lived blind spots.

Based on learnings, "In tests/integration/test_lists/waives.txt, prefer the short nvbug URL format https://nvbugs/XXXX ... ensure consistency by using the short form"; these new entries are consistent with that format.

Also applies to: 262-262, 338-345, 354-354

🤖 Prompt for 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.

In `@tests/integration/test_lists/waives.txt` at line 193, Add explicit follow-up
tasks (outside this PR) to restore CI coverage for each waived test file by
creating a tracker/ticket listing owner and target date:
tests/integration/disaggregated/test_disaggregated_single_gpu.py,
tests/integration/kv_cache/test_prefix_aware_scheduling.py,
tests/integration/unittest/_torch/multi_gpu/test_user_buffers.py (note 8
parametrized cases waived), and
tests/integration/unittest/auto_deploy/standalone/test_standalone_package.py;
ensure each tracker references the waiver lines (e.g., the waives.txt entries
around the mentioned ranges) and use the short nvbug URL format
(https://nvbugs/XXXX) in waives.txt for consistency.
🤖 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.

Nitpick comments:
In `@tests/integration/test_lists/waives.txt`:
- Line 193: Add explicit follow-up tasks (outside this PR) to restore CI
coverage for each waived test file by creating a tracker/ticket listing owner
and target date:
tests/integration/disaggregated/test_disaggregated_single_gpu.py,
tests/integration/kv_cache/test_prefix_aware_scheduling.py,
tests/integration/unittest/_torch/multi_gpu/test_user_buffers.py (note 8
parametrized cases waived), and
tests/integration/unittest/auto_deploy/standalone/test_standalone_package.py;
ensure each tracker references the waiver lines (e.g., the waives.txt entries
around the mentioned ranges) and use the short nvbug URL format
(https://nvbugs/XXXX) in waives.txt for consistency.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: d6240949-c93a-4bd1-9b56-7f5d68f73d9c

📥 Commits

Reviewing files that changed from the base of the PR and between 6dc60cb and a20e4ce.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #51936 [ run ] triggered by Bot. Commit: a20e4ce Link to invocation

@EmmaQiaoCh

Copy link
Copy Markdown
Collaborator

/bot skip --comment "The previous CI passed check test list"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #51954 [ skip ] triggered by Bot. Commit: a20e4ce Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #51936 [ run ] completed with state ABORTED. Commit: a20e4ce

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #51954 [ skip ] completed with state SUCCESS. Commit: a20e4ce
Skipping testing for commit a20e4ce

Link to invocation

@EmmaQiaoCh
EmmaQiaoCh merged commit 846d0f4 into NVIDIA:main Jun 4, 2026
12 checks passed
yufeiwu-nv pushed a commit to yufeiwu-nv/TensorRT-LLM that referenced this pull request Jun 4, 2026
…IA#14925)

Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants