Revert "[AMD] feat: Add mi355x distributed inference test CI workflow"#408
Revert "[AMD] feat: Add mi355x distributed inference test CI workflow"#408
Conversation
Summary of ChangesHello @cquil11, 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 systematically undoes the integration of a previously added CI workflow for AMD mi355x distributed inference tests. The change removes the associated configurations, benchmark scripts, and multi-node execution logic, effectively streamlining the CI pipeline by eliminating a feature that is no longer desired or functional. 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. 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]](proxy.php?url=https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request reverts a previous commit that added the mi355x distributed inference test CI workflow. The changes correctly remove the test configuration from .github/configs/amd-master.yaml, the associated benchmark script, the multi-node logic from the launch_mi355x-amd.sh runner, and the corresponding entry from perf-changelog.yaml. The revert appears to be complete and clean. As this is a revert consisting entirely of removals, I have no specific feedback on the code changes.
1 participant
Reverts InferenceMAX/InferenceMAX#401
Note
Reverts the MI355x disaggregated/multinode setup and associated CI artifacts.
dsr1-fp8-mi355x-sglang-disaggblock fromamd-master.yamland deletebenchmarks/dsr1_fp8_mi355x_sglang-disagg_slurm.shperf-changelog.yamlrunners/launch_mi355x-amd.shto single-node container launch; drop SLURM multinode orchestration, log collection, and cleanup logicOther configs (e.g.,
gptoss-fp4-mi355x-vllm) remain unchanged aside from surrounding context.Written by Cursor Bugbot for commit 091f445. This will update automatically on new commits. Configure here.