[None][chore] Update flashinfer-python from 0.6.12rc1 to 0.6.12rc2

[yihwang-nv]

Summary

• Bump flashinfer-python from 0.6.12rc1 to 0.6.12rc2 (latest pre-release on PyPI, published 2026-05-26)
• Switch requirements.txt and security_scanning/pyproject.toml from the git+ URL pin (used for 0.6.12rc1) back to a regular PyPI version pin, now that 0.6.12rc2 is published to PyPI
• Update version reference in ATTRIBUTIONS-Python.md

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 0.6.12rc1 to 0.6.12rc2 across project configuration files and attribution records.

[yihwang-nv]

/bot run --disable-fail-fast --add-multi-gpu-test

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR upgrades the flashinfer-python dependency from version 0.6.12rc1 to 0.6.12rc2 across the project's attribution records and Python dependency declarations, converting from git-based URL pins to direct PyPI version requirements.

Changes

Flashinfer Python Dependency Upgrade

Layer / File(s)	Summary
flashinfer-python 0.6.12rc1 → 0.6.12rc2 across all sources ATTRIBUTIONS-Python.md, requirements.txt, security_scanning/pyproject.toml	Updated attribution entry and changed requirements.txt from git-based tag-pinned install to PyPI ==0.6.12rc2. Updated security_scanning/pyproject.toml dependency from git tag to direct version pin.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14076: Both PRs bump the flashinfer-python dependency across the same three files with only version number changes.
• NVIDIA/TensorRT-LLM#14512: This PR's updates directly follow and modify the same dependency declarations using identical patterns.
• NVIDIA/TensorRT-LLM#13064: Both PRs coordinate flashinfer-python version updates across requirements.txt, security_scanning/pyproject.toml, and ATTRIBUTIONS-Python.md.

Suggested reviewers

• wenmingw
• juney-nvidia

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and concisely describes the main change: updating flashinfer-python from version 0.6.12rc1 to 0.6.12rc2, which is the primary objective of the PR.
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.
Description check	✅ Passed	The PR description clearly explains the changes (version bump from 0.6.12rc1 to 0.6.12rc2, switching from git URL to PyPI pins, updating attributions) and provides test coverage details.

_{✏️ 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.}

[tensorrt-cicd]

PR_Github #50433 [ run ] triggered by Bot. Commit: 9f9e0b1 Link to invocation

[tensorrt-cicd]

PR_Github #50433 [ run ] completed with state SUCCESS. Commit: 9f9e0b1
/LLM/main/L0_MergeRequest_PR pipeline #39955 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

[yihwang-nv]

/bot run --disable-fail-fast --add-multi-gpu-test

[tensorrt-cicd]

PR_Github #50561 [ run ] triggered by Bot. Commit: 9f9e0b1 Link to invocation

[tensorrt-cicd]

PR_Github #50561 [ run ] completed with state SUCCESS. Commit: 9f9e0b1
/LLM/main/L0_MergeRequest_PR pipeline #40062 completed with status: 'SUCCESS'

CI Report

Link to invocation