[None][chore] Update flashinfer-python from 0.6.8 to 0.6.9

[yihwang-nv]

Summary

• Bump flashinfer-python from 0.6.8 to 0.6.9 (latest stable, released 2026-04-24)
• Updated version pins in requirements.txt, security_scanning/pyproject.toml, security_scanning/poetry.lock, and ATTRIBUTIONS-Python.md
• Refreshed poetry.lock content-hash; transitively bumped nvidia-cutlass-dsl to 4.4.2 (added nvidia-cutlass-dsl-libs-base and cuda-tile to flashinfer's deps)
• The version-gated check in tensorrt_llm/_torch/speculative/interface.py (flashinfer.__version__ >= "0.6.4") remains satisfied

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 from version 0.6.8 to 0.6.9 across project configuration files.

[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: 7c2acdee-de43-439d-aa33-8aede47ba022

📥 Commits

Reviewing files that changed from the base of the PR and between 85a4618 and 6e53ca7.

⛔ Files ignored due to path filters (1)

• security_scanning/poetry.lock is excluded by !**/*.lock

📒 Files selected for processing (3)

• ATTRIBUTIONS-Python.md
• requirements.txt
• security_scanning/pyproject.toml

---

📝 Walkthrough

Walkthrough

This pull request updates the flashinfer-python dependency version from 0.6.8 to 0.6.9 across all dependency configuration files and attribution records in the project.

Changes

Cohort / File(s)	Summary
Flashinfer-Python Version Update ATTRIBUTIONS-Python.md, requirements.txt, security_scanning/pyproject.toml	Updates flashinfer-python pinned version from 0.6.8 to 0.6.9 across attribution documentation and dependency configurations.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• [None][chore] Update flashinfer-python from 0.6.6 to 0.6.8 #13064: Modifies the same dependency pins for flashinfer-python across the same files.

Suggested reviewers

• niukuo
• venkywonka
• hyukn
• wenmingw
• MartinMarciniszyn
• nv-guomingz
• yuxianq
• tburt-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: updating flashinfer-python from version 0.6.8 to 0.6.9, which matches the primary objective of the pull request.
Description check	✅ Passed	The pull request description provides a clear summary of changes, includes specific version updates across multiple files, mentions transitive dependency bumps, documents test coverage with completed checkboxes, and explains version-gated compatibility—comprehensively fulfilling the template requirements.
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

---

_{Review rate limit: 9/10 reviews remaining, refill in 6 minutes.}

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

[yihwang-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #46267 [ run ] triggered by Bot. Commit: 6e53ca7 Link to invocation

[yihwang-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #46307 [ run ] triggered by Bot. Commit: d768f99 Link to invocation

[tensorrt-cicd]

PR_Github #46307 [ run ] completed with state FAILURE. Commit: d768f99

Link to invocation

[yihwang-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #46312 [ run ] triggered by Bot. Commit: d768f99 Link to invocation

[tensorrt-cicd]

PR_Github #46312 [ run ] completed with state SUCCESS. Commit: d768f99
/LLM/main/L0_MergeRequest_PR pipeline #36413 completed with status: 'SUCCESS'

CI Report

Link to invocation

[juney-nvidia]

Approved from OSS compliance perspective.