docs: update benchmark documentation to reflect current HAMi usage#1750
docs: update benchmark documentation to reflect current HAMi usage#1750Yonsun-w wants to merge 1 commit into
Conversation
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: Yonsun-w The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
github-actions
Bot
added
the
kind/documentation
![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 benchmark documentation in both English and Chinese, designating older results as historical and adding a new section with instructions for running current benchmarks. The review feedback identifies several necessary corrections: standardizing directory paths to be relative to the repository root and fixing incorrect job names in the log retrieval commands to ensure they match the actual deployment configurations.
Fixes Project-HAMi#1722 This commit addresses the outdated benchmark documentation by: - Adding a clear notice that the historical benchmark data is from an older version (vGPU-device-plugin) - Updating terminology from "vGPU-device-plugin" to "HAMi" where appropriate - Adding a new "Running Benchmarks" section with up-to-date instructions - Providing clear steps for running benchmarks using the current HAMi deployment - Including instructions for both HAMi and NVIDIA device plugin benchmarks for comparison - Improving formatting consistency (capitalizing table headers) - Using paths relative to repository root (removed HAMi/ prefix) - Correcting job names to match actual deployment configurations Both English (benchmark.md) and Chinese (benchmark_cn.md) versions have been updated. The historical benchmark results are preserved for reference but clearly marked as legacy data. --- This PR was written primarily by Claude Code (Opus 4.6). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Wenjiahua <Wenjiahua@kanyun.com>
Yonsun-w
force-pushed
the
docs/update-benchmark-1722
branch
from
ea75d7e to
e631d56
Compare
Updates AppliedI've addressed all the AI-suggested improvements: Fixed Issues ✅
Changes Applied To:
All AI suggestions from the code review have been implemented. The DCO check is now passing ✅ |
| ``` | ||
|
|
||
| 3. View the result by using kubctl logs | ||
| For installing the official NVIDIA device plugin, refer to the [NVIDIA k8s-device-plugin Quick Start](https://github.com/NVIDIA/k8s-device-plugin?tab=readme-ov-file#quick-start). |
There was a problem hiding this comment.
@Yonsun-w I think it is better to replace For installing with To install
|
Hi, we've updated the benchmarks, please checkout the latest version |
|
@Yonsun-w two small issues:
|
|
Note: As of today, this issue/PR has been flagged under our new activity policy. If there is no response or update by July 18, 2026, it will be closed. It can be reopened at any time if still relevant. |
5 participants
Summary
This PR addresses issue #1722 by updating the outdated benchmark documentation.
Changes
Files Changed
docs/benchmark.md- English version updateddocs/benchmark_cn.md- Chinese version updatedThe historical benchmark results are preserved for reference but clearly marked as legacy data, ensuring users understand these numbers may not reflect current performance.
Test Plan
Related Issue
Fixes #1722
AI Assistance Disclosure: This PR was written primarily by Claude Code (Opus 4.6).
🤖 Generated with Claude Code