hotfix: add 9.0a to README and installation doc by yzh119 · Pull Request #2112 · flashinfer-ai/flashinfer

yzh119 · 2025-11-19T10:30:29Z

📌 Description

9.0a was removed from installation documentation by accident, in some recent PRs.

🔍 Related Issues

🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.

✅ Pre-commit Checks

I have installed pre-commit by running pip install pre-commit (or used your preferred method).
I have installed the hooks with pre-commit install.
I have run the hooks manually with pre-commit run --all-files and fixed any reported issues.

If you are unsure about how to set up pre-commit, see the pre-commit documentation.

🧪 Tests

Tests have been added or updated as needed.
All tests are passing (unittest, etc.).

Reviewer Notes

Summary by CodeRabbit

Release Notes

New Features
- Customizable Attention support
- CUDAGraph and torch.compile compatibility
- High-level LLM-specific operators
Documentation
- Expanded installation and setup guidance with improved build instructions
- Enhanced package options and adoption references
- Added support for additional CUDA architectures (9.0a, 12.0f)
- Faster offline initialization option documented

coderabbitai · 2025-11-19T10:30:41Z

Walkthrough

Documentation updates including new feature highlights (Customizable Attention, CUDAGraph/torch.compile compatibility, high-level LLM operators), expanded adoption references, enhanced installation guidance, and CUDA architecture support additions (9.0a, 12.0f) across README and installation docs.

Changes

Cohort / File(s)	Summary
Documentation Updates `README.md`, `docs/installation.rst`	Added feature highlights and usage notes; expanded News and Adoption sections; updated CUDA architecture list to include 9.0a and 12.0f in build instructions; enhanced package installation guidance with faster offline initialization notes and improved command examples; minor formatting adjustments

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Documentation-only changes with no code logic modifications
Additions are descriptive text, feature highlights, and CUDA configuration updates
No API changes or exported entity alterations

Poem

🐰 New features shine in the README bright,
CUDA arches expanded—9.0a takes flight!
Installation guides now sparkle anew,
With adoption tales and compiler tricks too,
The docs hop forward, hooray for the view! 🎉

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: restoring CUDA architecture 9.0a to both README and installation documentation after accidental removal.
Description check	✅ Passed	The description explains the purpose (restoring 9.0a), includes pre-commit checklist completion, and confirms tests are passing. Related Issues section is empty but non-critical.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between b9964cc and 7e5f86e.

📒 Files selected for processing (2)

README.md (6 hunks)
docs/installation.rst (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: Deploy Docs

🔇 Additional comments (3)

docs/installation.rst (1)

95-95: CUDA architecture list correctly restored.

The 9.0a architecture is properly added to FLASHINFER_CUDA_ARCH_LIST in ascending numerical order between 8.9 and 10.0a. This aligns with the README.md change and restores the inadvertently removed architecture support.

README.md (2)

99-99: CUDA architecture list correctly restored with consistent formatting.

The 9.0a addition matches the docs/installation.rst change and maintains proper ascending order in the export statement. Format is correct for bash shell commands.

23-30: Scope extends well beyond the PR title and objective.

The PR is titled "hotfix: add 9.0a" but includes substantial documentation additions: new core features (lines 23-30), expanded News section (lines 35-40), clarified Package Options (lines 54-68), updated Adoption section (lines 183-192), and verification output details (lines 130-133). While these changes appear legitimate and beneficial, please confirm whether they are intentional as part of this hotfix or represent unintended scope creep from a previous merge/rebase.

Also applies to: 35-40, 54-68, 81-84, 130-133, 183-192

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

gemini-code-assist · 2025-11-19T10:30:42Z

Summary of Changes

Hello @yzh119, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request provides a hotfix to correct an accidental omission in the project's documentation. It restores the 9.0a CUDA architecture version to the FLASHINFER_CUDA_ARCH_LIST environment variable examples, ensuring that users have accurate and complete information when building flashinfer-jit-cache from source. This change prevents potential issues related to unsupported or missing architecture configurations during the installation process.

Highlights

Documentation Correction: The 9.0a CUDA architecture version has been re-added to the FLASHINFER_CUDA_ARCH_LIST environment variable examples in both the README.md and docs/installation.rst files.
Formatting Improvements: Minor whitespace adjustments, primarily adding blank lines, have been made in the README.md file to improve readability.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request correctly adds 9.0a to the FLASHINFER_CUDA_ARCH_LIST in both README.md and docs/installation.rst, fixing an accidental removal. The changes are correct and address the issue described. I have one suggestion regarding commit hygiene to improve reviewability in the future, but the PR is good to merge.

gemini-code-assist · 2025-11-19T10:31:50Z

+
 ```bash
-export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 10.0a 10.3a 11.0a 12.0f"
+export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f"


The addition of 9.0a is correct. However, this PR mixes this logical change with numerous formatting adjustments (adding/removing blank lines) throughout the file, which were likely introduced by an auto-formatter. This makes the diff noisy and obscures the primary purpose of the hotfix. For future changes, it would be best to separate stylistic/formatting changes into a separate commit from functional or documentation content changes to improve reviewability.

9.0a was removed from installation documentation by accident, in some recent PRs.  Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.).

fix

7e5f86e

yzh119 requested review from aleozlx, cyx-6 and wenscarl as code owners November 19, 2025 10:30

yzh119 enabled auto-merge (squash) November 19, 2025 10:30

gemini-code-assist Bot reviewed Nov 19, 2025

View reviewed changes

cyx-6 approved these changes Nov 20, 2025

View reviewed changes

yzh119 merged commit 049e8db into flashinfer-ai:main Nov 20, 2025
4 checks passed

coderabbitai Bot mentioned this pull request Dec 10, 2025

docs: Document CUDA version support in README and installation page #2197

Merged

5 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

hotfix: add 9.0a to README and installation doc#2112

hotfix: add 9.0a to README and installation doc#2112
yzh119 merged 1 commit intoflashinfer-ai:mainfrom
yzh119:install-9.0a

yzh119 commented Nov 19, 2025 •

edited by coderabbitai Bot

Loading

Uh oh!

coderabbitai Bot commented Nov 19, 2025 •

edited

Loading

Uh oh!

gemini-code-assist Bot commented Nov 19, 2025

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

gemini-code-assist Bot Nov 19, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

yzh119 commented Nov 19, 2025 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

📌 Description

🔍 Related Issues

🚀 Pull Request Checklist

✅ Pre-commit Checks

🧪 Tests

Reviewer Notes

Summary by CodeRabbit

Release Notes

Uh oh!

coderabbitai Bot commented Nov 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Poem

Pre-merge checks and finishing touches

Uh oh!

gemini-code-assist Bot commented Nov 19, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot Nov 19, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

yzh119 commented Nov 19, 2025 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Nov 19, 2025 •

edited

Loading