[TRTLLM-12982][chore] improve multi-item scoring request validation

[ixlmar]

Description

Follow-up on review comments from #15416

Test Coverage

n/a

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.

Summary by CodeRabbit

• Bug Fixes
  • Added stricter validation for multi-item input lengths to catch invalid requests earlier.
  • Improved consistency checks in encoder-only workflows to prevent mismatched input lengths.
  • Refined internal position calculations for more reliable handling of multi-part inputs.

[ixlmar]

/bot run

[tensorrt-cicd]

PR_Github #55779 [ run ] triggered by Bot. Commit: e7e04be Link to invocation

[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: add66125-58c4-4a1d-a2a7-e699d7fa92de

📥 Commits

Reviewing files that changed from the base of the PR and between a8f0efc and e7e04be.

📒 Files selected for processing (2)

• tensorrt_llm/_torch/attention_backend/flashinfer.py
• tensorrt_llm/llmapi/llm.py

---

📝 Walkthrough

Walkthrough

Adds minimum-length validation for multi_item_part_lens in LLM.encode and _process_multi_item_part_lens, and rewrites flashinfer range_ends construction to use zip(..., strict=True) with chain().

Changes

Multi-item part_lens validation

Layer / File(s)	Summary
Encoder validation tensorrt_llm/llmapi/llm.py	LLM.encode now raises ValueError when multi_item_part_lens has fewer than two elements before the existing prompt-token length consistency check.
Flashinfer pointer construction tensorrt_llm/_torch/attention_backend/flashinfer.py	_process_multi_item_part_lens tightens short-input validation, adds chain, and rewrites range_ends construction with zip(..., strict=True) and a computed final delimiter.

Review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15413: Also changes multi_item_part_lens validation and multi-item preprocessing in tensorrt_llm/_torch/attention_backend/flashinfer.py.

Suggested reviewers

• hchings
• Funatiq
• litaotju

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is mostly a placeholder and does not explain the issue or the solution beyond referencing review comments.	Add a short summary of what changed and why, plus any relevant validation or test details beyond "n/a".
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 (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is specific, concise, and matches the main change: tighter validation for multi-item scoring requests.
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.}

[ixlmar]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #55800 [ run ] triggered by Bot. Commit: e7e04be Link to invocation

[tensorrt-cicd]

PR_Github #55779 [ run ] completed with state ABORTED. Commit: e7e04be

Link to invocation

[tensorrt-cicd]

PR_Github #55800 [ run ] completed with state SUCCESS. Commit: e7e04be
/LLM/main/L0_MergeRequest_PR pipeline #44695 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

[ixlmar]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #55875 [ run ] triggered by Bot. Commit: 63d0952 Link to invocation