Update DI SLO values and medium-priority model owners - #70
Open
yenuo26 wants to merge 7 commits into
Open
Conversation
- Updated the DI calculation guide with revised SLO values for high, medium, and low priority bugs. - Added a new section for medium priority models in the model owner documentation, including a list of models and their respective owners. These changes enhance clarity and provide updated information for better resource allocation and ownership tracking. Signed-off-by: wangyu <410167048@qq.com>
- Updated the 'owners' index with the latest modification date. - Added a new 'module_owner' document to track key modules and their respective owners for better routing during reviews and debugging. - Removed the medium priority models section from 'model_owner' documentation to streamline the content. These changes enhance the clarity and organization of ownership information within the vLLM-Omni project. Signed-off-by: wangyu <410167048@qq.com>
- Removed the high-priority section from 'model_owner' documentation to streamline content. - Updated 'module_owner' documentation with new owner assignments for several modules, including 'Benchmark/metrics/profiler', 'scheduler', 'Engine', and 'api_server'. These changes improve the clarity and accuracy of ownership information within the project. Signed-off-by: wangyu <410167048@qq.com>
- Changed the 'updated' date in the 'model_owner' documentation to reflect the accurate date of August 11, 2026. This update ensures the documentation remains current and reliable for users. Signed-off-by: wangyu <410167048@qq.com>
- Introduced a new document outlining release rules for vLLM-Omni, detailing pre-release requirements and acceptance criteria. - Added a new section for 'release' under the schema to categorize the release-related topics. - Updated the 'updated' date in the vLLM-Omni index to reflect the latest changes. These updates enhance the clarity and organization of release processes within the vLLM-Omni project. Signed-off-by: wangyu <410167048@qq.com>
- Revised the release guidelines to include CUDA L1 in the pass rate requirements, ensuring comprehensive coverage of all relevant CUDA levels. - Updated the NPU pass rate criteria to include L1, enhancing the clarity of performance expectations. These changes improve the accuracy and completeness of the release requirements for the vLLM-Omni project. Signed-off-by: wangyu <410167048@qq.com>
- Adjusted the formatting of the CUDA pass rate requirement for clarity, ensuring consistent spacing in the documentation. - This minor update enhances readability without altering the content or meaning of the release criteria. Signed-off-by: wangyu <410167048@qq.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
updateddates on the touched knowledge pagesTest plan
owners/_index.mdtomodel_owner.md