Skip to content

[https://nvbugs/6414762][fix] Minor fixes for helix tests - #15999

Merged
brb-nv merged 1 commit into
NVIDIA:mainfrom
brb-nv:user/brb/helix-disagg-failures
Jul 16, 2026
Merged

[https://nvbugs/6414762][fix] Minor fixes for helix tests#15999
brb-nv merged 1 commit into
NVIDIA:mainfrom
brb-nv:user/brb/helix-disagg-failures

Conversation

@brb-nv

@brb-nv brb-nv commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

@coderabbitai summary

Description

This MR addresses a couple of issues:

Background:

  • Previously, we turned a request-level assertion into a warning in [None][feat] Handle empty-block ranks with Helix CP #15383.
  • Turns out, this error is tripped only in unit tests (cacheTransceiverTest.cpp) and not integration tests because of a discrepancy in how the requests are constructed in the unit test.

This change makes unit test construct the request just the way integration test does so that we can bring the stronger assertion back.

Test Coverage

$ pytest tests/integration/defs/disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_bf16_tllm_gen_helix[DeepSeek-V3-Lite-bf16-short_prompt] -s -v
$ ./cpp/build/tests/unit_tests/executor/requestTest --gtest_filter=RequestTest.invalidInputs
$ TRTLLM_USE_UCX_KVCACHE=1 mpirun -n 8 ./cpp/build/tests/unit_tests/multi_gpu/cacheTransceiverTest --gtest_filter="*WithCP*"

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.

@brb-nv
brb-nv requested a review from a team as a code owner July 6, 2026 20:30
@brb-nv

brb-nv commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "A30-CPP-Post-Merge-1, A30-CPP-Post-Merge-2, DGX_B200-8_GPUs-PyTorch-1, DGX_B200-8_GPUs-PyTorch-2, DGX_B200-8_GPUs-PyTorch-3, DGX_B200-8_GPUs-PyTorch-4"

@coderabbitai

coderabbitai Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

📝 Walkthrough

Walkthrough

Changes enforce a strict non-empty check on input token IDs in the executor's request validation, replacing prior conditional warning logic. Test-side changes add a Blackwell-only skip decorator to a disaggregated test and remove two waive entries from the waives list.

Changes

Executor Request Validation

Layer / File(s) Summary
Enforce non-empty input token IDs
cpp/tensorrt_llm/executor/requestImpl.h
Request::Impl::validate() now unconditionally requires mInputTokenIds to be non-empty via TLLM_CHECK, removing the prior conditional warning-and-allow path; SPDX header year updated to 2025-2026.

Test Configuration Updates

Layer / File(s) Summary
Skip decorator and waive list cleanup
tests/integration/defs/disaggregated/test_disaggregated.py, tests/integration/test_lists/waives.txt
Adds @skip_pre_blackwell decorator to a disaggregated test, and removes waive entries for test_unit_tests[executor-80] and a DeepSeek-V3-Lite disaggregated test.

Estimated code review effort: 2 (Simple) | ~10 minutes

Possibly related PRs

Suggested reviewers: mzweilz, dongxuy04, pcastonguay

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
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.
Title check ✅ Passed The title matches the repository template and clearly summarizes the main fix set.
Description check ✅ Passed The description includes the required summary, description, test coverage, and checklist sections with relevant details.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57818 [ run ] triggered by Bot. Commit: 5ae56a5 Link to invocation

@brb-nv
brb-nv requested a review from ruodil July 6, 2026 21:40
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57818 [ run ] completed with state SUCCESS. Commit: 5ae56a5
/LLM/main/L0_MergeRequest_PR pipeline #46515 (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

@brb-nv

brb-nv commented Jul 7, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57869 [ run ] triggered by Bot. Commit: 5ae56a5 Link to invocation

@brb-nv
brb-nv enabled auto-merge (squash) July 7, 2026 02:42
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57869 [ run ] completed with state FAILURE. Commit: 5ae56a5
/LLM/main/L0_MergeRequest_PR pipeline #46565 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

@brb-nv
brb-nv force-pushed the user/brb/helix-disagg-failures branch from 5ae56a5 to d23fc4e Compare July 7, 2026 17:22
@brb-nv

brb-nv commented Jul 7, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #58046 [ run ] triggered by Bot. Commit: d23fc4e Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #58046 [ run ] completed with state FAILURE. Commit: d23fc4e
/LLM/main/L0_MergeRequest_PR pipeline #46714 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

@brb-nv
brb-nv force-pushed the user/brb/helix-disagg-failures branch from d23fc4e to 5ba9d2f Compare July 14, 2026 22:31
@brb-nv
brb-nv requested review from a team as code owners July 14, 2026 22:31
@brb-nv
brb-nv force-pushed the user/brb/helix-disagg-failures branch from 5ba9d2f to 6f9fe15 Compare July 14, 2026 22:55
@brb-nv
brb-nv force-pushed the user/brb/helix-disagg-failures branch from 6f9fe15 to b96d5b7 Compare July 15, 2026 00:10
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
@brb-nv
brb-nv force-pushed the user/brb/helix-disagg-failures branch from b96d5b7 to 388c148 Compare July 15, 2026 00:15
@brb-nv

brb-nv commented Jul 15, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@chzblych chzblych left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Approved for the tests/ modifications.

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59310 [ run ] triggered by Bot. Commit: 388c148 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59310 [ run ] completed with state SUCCESS. Commit: 388c148
/LLM/main/L0_MergeRequest_PR pipeline #47794 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

@brb-nv

brb-nv commented Jul 15, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59475 [ run ] triggered by Bot. Commit: 388c148 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59475 [ run ] completed with state SUCCESS. Commit: 388c148
/LLM/main/L0_MergeRequest_PR pipeline #47940 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

@brb-nv

brb-nv commented Jul 15, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59508 [ run ] triggered by Bot. Commit: 388c148 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59508 [ run ] completed with state SUCCESS. Commit: 388c148
/LLM/main/L0_MergeRequest_PR pipeline #47965 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

@brb-nv

brb-nv commented Jul 15, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59534 [ run ] triggered by Bot. Commit: 388c148 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59534 [ run ] completed with state FAILURE. Commit: 388c148
/LLM/main/L0_MergeRequest_PR pipeline #47985 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

@brb-nv

brb-nv commented Jul 15, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59552 [ run ] triggered by Bot. Commit: 388c148 Link to invocation

@brb-nv

brb-nv commented Jul 16, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59560 [ run ] triggered by Bot. Commit: 388c148 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59552 [ run ] completed with state ABORTED. Commit: 388c148

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59560 [ run ] completed with state SUCCESS. Commit: 388c148
/LLM/main/L0_MergeRequest_PR pipeline #48005 completed with status: 'SUCCESS'

CI Report

Link to invocation

@brb-nv
brb-nv merged commit a914fe4 into NVIDIA:main Jul 16, 2026
13 checks passed
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.

7 participants