[None][chore] Update flashinfer-python from 0.6.9 to 0.6.10

[yihwang-nv]

Summary

• Bump flashinfer-python from 0.6.9 to 0.6.10 (latest stable, released 2026-05-04).
• Update version pins in requirements.txt, security_scanning/pyproject.toml, security_scanning/poetry.lock, and ATTRIBUTIONS-Python.md.
• Replace string version comparison with packaging.version.Version in tensorrt_llm/_torch/speculative/interface.py so the >= 0.6.4 gate evaluates correctly. Lexicographic compare gave "0.6.10" >= "0.6.4" → False, which would have silently disabled flashinfer in SpecWorkerBase after the bump.

Test plan

• pip install -r requirements.txt installs successfully
• pytest tests/unittest/_torch/flashinfer/ -v
• pytest tests/unittest/_torch/attention/test_flashinfer_attention.py -v
• CI pre-merge passes

Summary by CodeRabbit

• Chores

  • Updated flashinfer-python dependency to version 0.6.10 across all project configurations.

• Bug Fixes

  • Improved version compatibility checking to use proper semantic versioning comparison for better accuracy.

[yihwang-nv]

/bot run --disable-fail-fast

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR bumps flashinfer-python from version 0.6.9 to 0.6.10 across dependency manifests and updates the FlashInfer availability check to use semantic version comparison via packaging.version.Version instead of lexicographic string comparison.

Changes

FlashInfer Dependency Update

Layer / File(s)	Summary
Dependency Manifest Updates requirements.txt, security_scanning/pyproject.toml	FlashInfer pinned version incremented from 0.6.9 to 0.6.10 in project dependency specifications.
Version Comparison Logic tensorrt_llm/_torch/speculative/interface.py	Import Version from packaging.version and update FlashInfer availability check to use semantic version comparison (Version(flashinfer.__version__) >= Version("0.6.4")) instead of string comparison.
Documentation ATTRIBUTIONS-Python.md	Attribution entry for flashinfer-python updated from 0.6.9 to 0.6.10.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#13631: Both PRs bump flashinfer-python and update the same dependency and attribution files.

Suggested reviewers

• wenmingw
• hyukn

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: updating flashinfer-python from 0.6.9 to 0.6.10, and follows the repository's naming convention with [None][chore] prefix.
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.
Description check	✅ Passed	The pull request description provides a clear summary of changes, specific version bump details, explanation of the critical bug fix (lexicographic string comparison issue), and a comprehensive test plan with checkmarks indicating verification.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

Tip

💬 Introducing Slack Agent: The best way for teams to turn conversations into code.

Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.

• Generate code and open pull requests
• Plan features and break down work
• Investigate incidents and troubleshoot customer tickets together
• Automate recurring tasks and respond to alerts with triggers
• Summarize progress and report instantly

Built for teams:

• Shared memory across your entire org—no repeating context
• Per-thread sandboxes to safely plan and execute work
• Governance built-in—scoped access, auditability, and budget controls

One agent for your entire SDLC. Right inside Slack.

👉 Get started

---

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

[tensorrt-cicd]

PR_Github #46727 [ run ] triggered by Bot. Commit: d199a79 Link to invocation

[yihwang-nv]

/bot run

[yihwang-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #46769 [ run ] triggered by Bot. Commit: da4929c Link to invocation

[tensorrt-cicd]

PR_Github #46770 [ run ] triggered by Bot. Commit: da4929c Link to invocation

[tensorrt-cicd]

PR_Github #46769 [ run ] completed with state ABORTED. Commit: da4929c

Link to invocation

[tensorrt-cicd]

PR_Github #46727 [ run ] completed with state ABORTED. Commit: d199a79

Link to invocation

[tensorrt-cicd]

PR_Github #46770 [ run ] completed with state SUCCESS. Commit: da4929c
/LLM/main/L0_MergeRequest_PR pipeline #36793 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation

[juney-nvidia]

Approved from the perspective of spec decoding related changes.