[None][chore] Update flashinfer-python from 0.6.16 to 0.6.18 by nv-guomingz · Pull Request #18428 · NVIDIA/TensorRT-LLM

nv-guomingz · 2026-08-31T06:05:08Z

Summary

Bump flashinfer-python from 0.6.16 to 0.6.18 (latest stable).

Updated version pins in:

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

Notable upstream changes relevant to TRT-LLM:

SM100 GDN chunk-scan prefill optimization ([GDN] improve sm100 GDN performance flashinfer-ai/flashinfer#4133)
SM100 GDN state-update correctness fix (fix(gdn): use block-end decay for SM100 state updates flashinfer-ai/flashinfer#4311)
GDN/MTP kernel reuse across cache modes, reducing JIT instances (perf(gdn): reuse MTP decode kernels across cache modes flashinfer-ai/flashinfer#4128, [TRTLLM-5085][fix] Nemotron H correctness test #4444)

Test Coverage

Existing FlashInfer attention/GDN unit tests in CI
pip install -r requirements.txt installs successfully
CI pre-merge passes

Summary by CodeRabbit

Chores
- Updated flashinfer-python dependency from 0.6.16 to 0.6.18

Dev Engineer Review

Updated flashinfer-python from 0.6.16 to 0.6.18 in:
- requirements.txt
- security_scanning/pyproject.toml
- ATTRIBUTIONS-Python.md
Dependency versions remain consistent across all files.
No public API or test files changed.
The update includes upstream SM100 GDN optimizations, a correctness fix, and kernel reuse improvements.
Installation and CI pre-merge checks passed.
The L0 Merge Request pipelines failed. The failed tests require follow-up before merge.

QA Engineer Review

No test changes.

nv-guomingz · 2026-08-31T06:05:20Z

/bot run

coderabbitai · 2026-08-31T06:09:28Z

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: ec1b8eb3-c6d5-40f3-b046-462d58e50400

📥 Commits

Reviewing files that changed from the base of the PR and between 5a1ae8f and 05d94f4.

📒 Files selected for processing (3)

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

🚧 Files skipped from review as they are similar to previous changes (3)

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

Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review.

Walkthrough

The PR updates flashinfer-python from version 0.6.16 to 0.6.18 in the main requirements, security scanning configuration, and attribution record.

Changes

FlashInfer dependency update

Layer / File(s)	Summary
Update FlashInfer version references `requirements.txt`, `security_scanning/pyproject.toml`, `ATTRIBUTIONS-Python.md`	The dependency pins and attribution record now reference `flashinfer-python` version `0.6.18`.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Merge Risk: ⚪ Minimal · up to 05d94

This change updates the flashinfer-python dependency and matching attribution metadata without any identified merge-blocking risk; it is merge-ready after normal checks and review.

Suggested reviewers: mlefeb01, zhanruisunch

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the dependency update from flashinfer-python 0.6.16 to 0.6.18 and uses the required ticket and type format.
Description check	✅ Passed	The description explains the dependency update, lists the affected files, notes relevant upstream changes, and documents test coverage. It does not include the PR Checklist section, but the required c…
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
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.

Full details: Description check

Explanation

The description explains the dependency update, lists the affected files, notes relevant upstream changes, and documents test coverage. It does not include the PR Checklist section, but the required change and validation information is mostly complete.

Full details: Docstring Coverage

Explanation

No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0 files. (3 skipped: 3 unsupported.)

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

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

tensorrt-cicd · 2026-08-31T06:12:33Z

PR_Github #70268 [ run ] triggered by Bot. Commit: 34e6d00 Link to invocation

tensorrt-cicd · 2026-08-31T08:24:10Z

PR_Github #70268 [ run ] completed with state SUCCESS. Commit: 34e6d00
/LLM/main/L0_MergeRequest_PR pipeline #57515 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

coderabbitai · 2026-09-01T10:36:15Z

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

nv-guomingz · 2026-09-01T10:36:24Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-09-01T10:43:39Z

PR_Github #70676 [ run ] triggered by Bot. Commit: e935430 Link to invocation

tensorrt-cicd · 2026-09-01T14:23:31Z

PR_Github #70676 [ run ] completed with state SUCCESS. Commit: e935430
/LLM/main/L0_MergeRequest_PR pipeline #57874 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

Bump flashinfer-python to the latest stable release. Updated version pins in requirements.txt, security_scanning/pyproject.toml, and ATTRIBUTIONS-Python.md. Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

coderabbitai · 2026-09-02T02:44:29Z

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

nv-guomingz · 2026-09-02T02:45:22Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-09-02T02:53:17Z

PR_Github #70875 [ run ] triggered by Bot. Commit: 05d94f4 Link to invocation

tensorrt-cicd · 2026-09-02T12:14:24Z

PR_Github #70875 [ run ] completed with state SUCCESS. Commit: 05d94f4
/LLM/main/L0_MergeRequest_PR pipeline #58049 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

nv-guomingz · 2026-09-02T12:21:30Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-09-02T12:28:04Z

PR_Github #70985 [ run ] triggered by Bot. Commit: 05d94f4 Link to invocation

tensorrt-cicd · 2026-09-02T13:48:24Z

PR_Github #70985 [ run ] completed with state SUCCESS. Commit: 05d94f4
/LLM/main/L0_MergeRequest_PR pipeline #58146 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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

Link to invocation

nv-guomingz · 2026-09-03T02:21:08Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-09-03T02:29:50Z

PR_Github #71126 [ run ] triggered by Bot. Commit: 05d94f4 Link to invocation

tensorrt-cicd · 2026-09-03T04:59:06Z

PR_Github #71126 [ run ] completed with state FAILURE. Commit: 05d94f4
/LLM/main/L0_MergeRequest_PR pipeline #58270 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

nv-guomingz · 2026-09-03T05:01:37Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-09-03T05:07:59Z

PR_Github #71178 [ run ] triggered by Bot. Commit: 05d94f4 Link to invocation

tensorrt-cicd · 2026-09-03T06:12:52Z

PR_Github #71178 [ run ] completed with state SUCCESS. Commit: 05d94f4
/LLM/main/L0_MergeRequest_PR pipeline #58315 completed with status: 'SUCCESS'

CI Report

Link to invocation

nv-guomingz requested review from a team as code owners August 31, 2026 06:05

nv-guomingz requested review from ZhanruiSunCh and mlefeb01 August 31, 2026 06:05

github-actions Bot assigned nv-guomingz Aug 31, 2026

nv-guomingz force-pushed the nv-guomingz/update_flashinfer_0.6.18 branch from 34e6d00 to e935430 Compare September 1, 2026 10:36

tburt-nv approved these changes Sep 1, 2026

View reviewed changes

nv-guomingz force-pushed the nv-guomingz/update_flashinfer_0.6.18 branch from e935430 to 05d94f4 Compare September 2, 2026 02:44

yuxianq mentioned this pull request Sep 2, 2026

[None][chore] Update flashinfer-python from 0.6.16 to 0.6.18 #18589

Closed

1 task

yuxianq approved these changes Sep 2, 2026

View reviewed changes

Shixiaowei02 added the ci: full pre-merge approved label Sep 3, 2026

nv-guomingz enabled auto-merge (squash) September 3, 2026 05:02

nv-guomingz merged commit 31779d6 into NVIDIA:main Sep 3, 2026
14 checks passed

Uh oh!

Conversation

nv-guomingz commented Aug 31, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Test Coverage

Summary by CodeRabbit

Dev Engineer Review

QA Engineer Review

Uh oh!

nv-guomingz commented Aug 31, 2026

Uh oh!

coderabbitai Bot commented Aug 31, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Uh oh!

tensorrt-cicd commented Aug 31, 2026

Uh oh!

tensorrt-cicd commented Aug 31, 2026

Uh oh!

coderabbitai Bot commented Sep 1, 2026

Uh oh!

nv-guomingz commented Sep 1, 2026

Uh oh!

tensorrt-cicd commented Sep 1, 2026

Uh oh!

tensorrt-cicd commented Sep 1, 2026

Uh oh!

coderabbitai Bot commented Sep 2, 2026

Uh oh!

nv-guomingz commented Sep 2, 2026

Uh oh!

tensorrt-cicd commented Sep 2, 2026

Uh oh!

tensorrt-cicd commented Sep 2, 2026

Uh oh!

nv-guomingz commented Sep 2, 2026

Uh oh!

tensorrt-cicd commented Sep 2, 2026

Uh oh!

tensorrt-cicd commented Sep 2, 2026

Uh oh!

nv-guomingz commented Sep 3, 2026

Uh oh!

tensorrt-cicd commented Sep 3, 2026

Uh oh!

tensorrt-cicd commented Sep 3, 2026

Uh oh!

nv-guomingz commented Sep 3, 2026

Uh oh!

tensorrt-cicd commented Sep 3, 2026

Uh oh!

tensorrt-cicd commented Sep 3, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

nv-guomingz commented Aug 31, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Aug 31, 2026 •

edited

Loading