Conversation
📝 WalkthroughWalkthroughThis pull request bumps the version number in version.txt from 0.6.5 to 0.6.6. The change is a single-line version metadata update with no modifications to code logic, structure, or functionality. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~1 minute Possibly related PRs
Suggested labels
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
Summary of ChangesHello, 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 primarily focuses on updating the version number to 0.6.6 and incorporates API modifications related to the gated delta rule functions. It is intended to bundle several related changes marked with the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe 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
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 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. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request updates the version from 0.6.5 to 0.6.6. Based on the API changes noted in the pull request description, particularly a change in a default parameter value which could be a breaking change, I've suggested considering a minor version bump to 0.7.0 instead, in adherence with semantic versioning principles.
Note: Security Review has been skipped due to the limited scope of the PR.
| @@ -1 +1 @@ | |||
| 0.6.5 | |||
| 0.6.6 | |||
There was a problem hiding this comment.
Given the API changes mentioned in the pull request description, specifically the change of the default value for disable_state_update in gated_delta_rule_mtp from True to False, this could be a breaking change for users who were relying on the previous default behavior. According to semantic versioning practices for projects in version 0.x, introducing breaking changes should result in a minor version bump. A patch version is typically for backward-compatible bug fixes. Therefore, a version bump to 0.7.0 might be more appropriate for this release.
0.7.0
|
/bot run |
|
[SUCCESS] Pipeline #45728223: 10/20 passed |
<!-- .github/pull_request_template.md --> ## 📌 Description <!-- What does this PR do? Briefly describe the changes and why they’re needed. --> ## 🔍 "Gated-by" PR list https://github.com/flashinfer-ai/flashinfer/pulls?q=is%3Aopen+is%3Apr+label%3Av0.6.6 flashinfer-ai#2730 Resolving gated_delta_rule_mtp breaking change before release ## 🚀 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](https://pre-commit.com/). ## 🧪 Tests - [ ] Tests have been added or updated as needed. - [ ] All tests are passing (`unittest`, etc.). ## Reviewer Notes **API changes review** ```diff $ git diff v0.6.5 | grep -A20 @flashinfer_api (version_bump✱) @flashinfer_api def gated_delta_rule_decode_pretranspose( q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, - state: torch.Tensor, + state: Optional[torch.Tensor], A_log: torch.Tensor, a: torch.Tensor, dt_bias: torch.Tensor, @@ -951,6 +113,8 @@ def gated_delta_rule_decode_pretranspose( scale: Optional[float] = None, output: Optional[torch.Tensor] = None, use_qk_l2norm: bool = True, + initial_state: Optional[torch.Tensor] = None, + initial_state_indices: Optional[torch.Tensor] = None, ) -> Tuple[torch.Tensor, torch.Tensor]: r"""Gated Delta Rule Decode kernel for single-token generation. @@ -964,10 +128,11 @@ def gated_delta_rule_decode_pretranspose( Current key of shape ``[B, 1, H, K]``. Must be float16/bfloat16. -- @flashinfer_api def gated_delta_rule_mtp( q: torch.Tensor, @@ -2398,7 +487,7 @@ def gated_delta_rule_mtp( scale: Optional[float] = None, output: Optional[torch.Tensor] = None, intermediate_states_buffer: Optional[torch.Tensor] = None, - disable_state_update: bool = True, + disable_state_update: bool = False, use_qk_l2norm: bool = True, ) -> Tuple[torch.Tensor, torch.Tensor]: """ ``` * gated_delta_rule_mtp will be resolved in PR flashinfer-ai#2730 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Chores** * Version bump to 0.6.6 <!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md --> ## 📌 Description <!-- What does this PR do? Briefly describe the changes and why they’re needed. --> ## 🔍 "Gated-by" PR list https://github.com/flashinfer-ai/flashinfer/pulls?q=is%3Aopen+is%3Apr+label%3Av0.6.6 flashinfer-ai#2730 Resolving gated_delta_rule_mtp breaking change before release ## 🚀 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](https://pre-commit.com/). ## 🧪 Tests - [ ] Tests have been added or updated as needed. - [ ] All tests are passing (`unittest`, etc.). ## Reviewer Notes **API changes review** ```diff $ git diff v0.6.5 | grep -A20 @flashinfer_api (version_bump✱) @flashinfer_api def gated_delta_rule_decode_pretranspose( q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, - state: torch.Tensor, + state: Optional[torch.Tensor], A_log: torch.Tensor, a: torch.Tensor, dt_bias: torch.Tensor, @@ -951,6 +113,8 @@ def gated_delta_rule_decode_pretranspose( scale: Optional[float] = None, output: Optional[torch.Tensor] = None, use_qk_l2norm: bool = True, + initial_state: Optional[torch.Tensor] = None, + initial_state_indices: Optional[torch.Tensor] = None, ) -> Tuple[torch.Tensor, torch.Tensor]: r"""Gated Delta Rule Decode kernel for single-token generation. @@ -964,10 +128,11 @@ def gated_delta_rule_decode_pretranspose( Current key of shape ``[B, 1, H, K]``. Must be float16/bfloat16. -- @flashinfer_api def gated_delta_rule_mtp( q: torch.Tensor, @@ -2398,7 +487,7 @@ def gated_delta_rule_mtp( scale: Optional[float] = None, output: Optional[torch.Tensor] = None, intermediate_states_buffer: Optional[torch.Tensor] = None, - disable_state_update: bool = True, + disable_state_update: bool = False, use_qk_l2norm: bool = True, ) -> Tuple[torch.Tensor, torch.Tensor]: """ ``` * gated_delta_rule_mtp will be resolved in PR flashinfer-ai#2730 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Chores** * Version bump to 0.6.6 <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: Amey Naik <212485788+ameynaik-hub@users.noreply.github.com>
4 participants
📌 Description
🔍 "Gated-by" PR list
https://github.com/flashinfer-ai/flashinfer/pulls?q=is%3Aopen+is%3Apr+label%3Av0.6.6
#2730 Resolving gated_delta_rule_mtp breaking change before release
🚀 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
pre-commitby runningpip install pre-commit(or used your preferred method).pre-commit install.pre-commit run --all-filesand fixed any reported issues.🧪 Tests
unittest, etc.).Reviewer Notes
API changes review
$ git diff v0.6.5 | grep -A20 @flashinfer_api (version_bump✱) @flashinfer_api def gated_delta_rule_decode_pretranspose( q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, - state: torch.Tensor, + state: Optional[torch.Tensor], A_log: torch.Tensor, a: torch.Tensor, dt_bias: torch.Tensor, @@ -951,6 +113,8 @@ def gated_delta_rule_decode_pretranspose( scale: Optional[float] = None, output: Optional[torch.Tensor] = None, use_qk_l2norm: bool = True, + initial_state: Optional[torch.Tensor] = None, + initial_state_indices: Optional[torch.Tensor] = None, ) -> Tuple[torch.Tensor, torch.Tensor]: r"""Gated Delta Rule Decode kernel for single-token generation. @@ -964,10 +128,11 @@ def gated_delta_rule_decode_pretranspose( Current key of shape ``[B, 1, H, K]``. Must be float16/bfloat16. -- @flashinfer_api def gated_delta_rule_mtp( q: torch.Tensor, @@ -2398,7 +487,7 @@ def gated_delta_rule_mtp( scale: Optional[float] = None, output: Optional[torch.Tensor] = None, intermediate_states_buffer: Optional[torch.Tensor] = None, - disable_state_update: bool = True, + disable_state_update: bool = False, use_qk_l2norm: bool = True, ) -> Tuple[torch.Tensor, torch.Tensor]: """Summary by CodeRabbit