[None][chore] Update flashinfer-python from 0.6.10 to 0.6.11 by yihwang-nv · Pull Request #13992 · NVIDIA/TensorRT-LLM

yihwang-nv · 2026-05-11T09:29:23Z

Summary

Bump flashinfer-python from 0.6.10 to 0.6.11 (latest stable)
Bump nvidia-cutlass-dsl from 4.4.2 to 4.5.0 (required by flashinfer-python 0.6.11)
Updated version pins in requirements.txt, security_scanning/pyproject.toml, and 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 and nvidia-cutlass-dsl package versions across project dependencies for improved compatibility and stability.

coderabbitai · 2026-05-11T09:32:59Z

📝 Walkthrough

Walkthrough

This PR bumps two pinned dependencies: flashinfer-python from 0.6.10 to 0.6.11 and nvidia-cutlass-dsl from 4.4.2 to 4.5.0. Updates are synchronized across the main requirements file, security scanning configuration, and attribution documentation.

Changes

Dependency Version Updates

Layer / File(s)	Summary
Primary Dependencies `requirements.txt`	`flashinfer-python==0.6.10` → `0.6.11` and `nvidia-cutlass-dsl==4.4.2` → `4.5.0` for Python >= 3.10.
Security Scanning Configuration `security_scanning/pyproject.toml`	Matching version pins updated to `flashinfer-python==0.6.11` and `nvidia-cutlass-dsl==4.5.0` in project dependencies.
Attribution Documentation `ATTRIBUTIONS-Python.md`	Version references in attribution headers updated for both dependencies.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	PR description is clear and well-structured, covering the changes and test coverage, but lacks alignment with the repository's description template.	Follow the template structure: add title with [ticket][type] format, include proper sections (Description, Test Coverage, PR Checklist), and confirm all checklist items are addressed.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: updating flashinfer-python dependency version, which is the primary focus of the PR despite also bumping nvidia-cutlass-dsl.
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

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.}

coderabbitai

Actionable comments posted: 4

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@requirements.txt`:
- Line 57: Update the pip requirement for the flashinfer-python dependency to a
published version: replace the nonexistent version token
"flashinfer-python==0.6.11" with the available release
"flashinfer-python==0.6.10" in requirements.txt so installation succeeds.
- Line 74: Replace the invalid hard-pin of nvidia-cutlass-dsl==4.5.0 in
requirements.txt: update the line referencing "nvidia-cutlass-dsl==4.5.0;
python_version >= \"3.10\"" to either a valid release (e.g.,
"nvidia-cutlass-dsl==4.4.2; python_version >= \"3.10\"") or a minimal constraint
that satisfies consumers (e.g., "nvidia-cutlass-dsl>=4.4.2; python_version >=
\"3.10\""), ensuring compatibility with flashinfer-python's requirement and that
pip can install the package.

In `@security_scanning/pyproject.toml`:
- Line 58: The pinned dependency "flashinfer-python (==0.6.11)" is referencing a
non-existent stable PyPI release; update the constraint to a valid package
version such as "flashinfer-python (==0.6.10.post1)" or use a permissive
constraint like "flashinfer-python (>=0.6.10.post1,<0.7)" if you want to allow
newer/stable builds; edit the pyproject.toml dependency entry to replace
"==0.6.11" with the chosen valid version or range so installations from PyPI
succeed.
- Line 75: The pyproject dependency "nvidia-cutlass-dsl (==4.5.0)" is pinned to
a non-existent stable 4.5.0 on PyPI; update that requirement to a valid release
such as "nvidia-cutlass-dsl (==4.5.0.dev0)" or relax to a compatible constraint
like "nvidia-cutlass-dsl (>=4.4.2)" to match flashinfer-python's requirement and
ensure dependency resolution succeeds.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 74a86829-0c43-42a0-b5bd-65509aadaa2c

📥 Commits

Reviewing files that changed from the base of the PR and between 9547230 and bf4c658.

⛔ 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

yihwang-nv · 2026-05-11T09:55:31Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-05-11T10:01:39Z

PR_Github #47722 [ run ] triggered by Bot. Commit: bf4c658 Link to invocation

tensorrt-cicd · 2026-05-11T15:02:31Z

PR_Github #47722 [ run ] completed with state SUCCESS. Commit: bf4c658
/LLM/main/L0_MergeRequest_PR pipeline #37618 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 · 2026-05-11T15:25:16Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-05-11T15:31:03Z

PR_Github #47765 [ run ] triggered by Bot. Commit: bf4c658 Link to invocation

tensorrt-cicd · 2026-05-11T17:23:04Z

PR_Github #47765 [ run ] completed with state SUCCESS. Commit: bf4c658
/LLM/main/L0_MergeRequest_PR pipeline #37657 completed with status: 'SUCCESS'

CI Report

Link to invocation

Bump flashinfer-python dependency to the latest stable release (0.6.11). Also bump nvidia-cutlass-dsl from 4.4.2 to 4.5.0 as required by flashinfer-python 0.6.11. Updated version pins in requirements.txt, security_scanning/pyproject.toml, and ATTRIBUTIONS-Python.md. Signed-off-by: Yihan Wang <[email protected]>

yihwang-nv · 2026-05-12T11:28:22Z

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

tensorrt-cicd · 2026-05-12T11:33:40Z

PR_Github #47958 [ run ] triggered by Bot. Commit: cf8d9af Link to invocation

tensorrt-cicd · 2026-05-12T20:47:23Z

PR_Github #47958 [ run ] completed with state SUCCESS. Commit: cf8d9af
/LLM/main/L0_MergeRequest_PR pipeline #37799 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 · 2026-05-13T02:24:10Z

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

tensorrt-cicd · 2026-05-13T02:29:19Z

PR_Github #48071 [ run ] triggered by Bot. Commit: cf8d9af Link to invocation

tensorrt-cicd · 2026-05-13T04:08:41Z

PR_Github #48071 [ run ] completed with state SUCCESS. Commit: cf8d9af
/LLM/main/L0_MergeRequest_PR pipeline #37903 completed with status: 'SUCCESS'

CI Report

Link to invocation

juney-nvidia

Approved from OSS compliance perspective.

…13992) Signed-off-by: Yihan Wang <[email protected]>

yihwang-nv requested a review from a team as a code owner May 11, 2026 09:29

github-actions Bot assigned yihwang-nv May 11, 2026

coderabbitai Bot reviewed May 11, 2026

View reviewed changes

Comment thread requirements.txt

Comment thread requirements.txt

Comment thread security_scanning/pyproject.toml

Comment thread security_scanning/pyproject.toml

yihwang-nv force-pushed the yihwang-nv/update_flashinfer_0.6.11 branch from bf4c658 to cf8d9af Compare May 12, 2026 11:27

yihwang-nv enabled auto-merge (squash) May 13, 2026 04:46

juney-nvidia approved these changes May 13, 2026

View reviewed changes

yihwang-nv merged commit 1a8f5ab into NVIDIA:main May 13, 2026
12 of 15 checks passed

coderabbitai Bot mentioned this pull request May 13, 2026

[None][chore] Update flashinfer-python from 0.6.11 to 0.6.11.post1 #14076

Merged

4 tasks

yufeiwu-nv pushed a commit to yufeiwu-nv/TensorRT-LLM that referenced this pull request May 19, 2026

[None][chore] Update flashinfer-python from 0.6.10 to 0.6.11 (NVIDIA#…

4cb6562

…13992) Signed-off-by: Yihan Wang <[email protected]>

This was referenced May 20, 2026

User/itabrizian/fix disagg gen init history length #14376

Closed

[None][chore] Update flashinfer-python from 0.6.11.post1 to 0.6.12rc1 #14512

Merged

Conversation

yihwang-nv commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Test plan

Summary by CodeRabbit

Uh oh!

coderabbitai Bot commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

❌ Failed checks (1 inconclusive)

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

yihwang-nv commented May 11, 2026

Uh oh!

tensorrt-cicd commented May 11, 2026

Uh oh!

tensorrt-cicd commented May 11, 2026

Uh oh!

yihwang-nv commented May 11, 2026

Uh oh!

tensorrt-cicd commented May 11, 2026

Uh oh!

tensorrt-cicd commented May 11, 2026

Uh oh!

yihwang-nv commented May 12, 2026

Uh oh!

tensorrt-cicd commented May 12, 2026

Uh oh!

tensorrt-cicd commented May 12, 2026

Uh oh!

yihwang-nv commented May 13, 2026

Uh oh!

tensorrt-cicd commented May 13, 2026

Uh oh!

tensorrt-cicd commented May 13, 2026

Uh oh!

juney-nvidia left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

yihwang-nv commented May 11, 2026 •

edited

Loading

coderabbitai Bot commented May 11, 2026 •

edited

Loading