Revert "[AMD] Add mi355x distributed inference test CI workflow"#400
Revert "[AMD] Add mi355x distributed inference test CI workflow"#400
Conversation
This reverts commit c4bbfb4.
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 performs a complete revert of a previous change (InferenceMAX/InferenceMAX#348) that introduced a CI workflow for AMD MI355X distributed inference tests. The revert removes all associated configuration, benchmark scripts, and runner logic, effectively undoing the integration of these specific tests from the system. 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 the changes from PR #348, removing the mi355x distributed inference test CI workflow. The changes correctly remove the configuration from amd-master.yaml, delete the dsr1_fp8_mi355x_sglang-disagg_slurm.sh benchmark script, prune the perf-changelog.yaml, and simplify runners/launch_mi355x-amd.sh to a single-node path.
My review found one issue: an extra newline was added at the beginning of benchmarks/dsr1_fp8_gb200_dynamo-sglang_slurm.sh, which misplaces the shebang and can cause execution problems. I've added a comment with a suggestion to fix this. Otherwise, the revert appears to be correct and complete.
|
|
||
| #!/bin/bash |
There was a problem hiding this comment.
The shebang (#!/bin/bash) must be on the very first line of a shell script. The added blank line at the beginning of the file can cause the script to be executed by the wrong interpreter if run directly, which can lead to errors. Please remove the leading blank line.
| #!/bin/bash | |
| #!/bin/bash |
![cursor[bot]](proxy.php?url=https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
| @@ -1,3 +1,4 @@ | |||
|
|
|||
There was a problem hiding this comment.
Empty line before shebang breaks script execution
Medium Severity
This revert accidentally adds an empty line before the shebang (#!/bin/bash), moving it from line 1 to line 2. The shebang must be on the first line of the file for the kernel to recognize the script interpreter when executed directly. While this script may still work when invoked explicitly with bash, direct execution (e.g., ./script.sh) will fail or behave unexpectedly.
* Revert "Revert "[AMD] Add mi355x distributed inference test CI workflow (#348)" (#400) [skip-sweep]" This reverts commit a075f2e. * add random range ratio that is appropriate (#402) * comment out 1k8k 8k1k * change recipe back to upstream * revert comment out 1k8k 8k1k * Add empty line at the beginning of the script --------- Co-authored-by: billishyahao <[email protected]>
1 participant
Reverts InferenceMAX/InferenceMAX#348
Note
Reverts MI355x disaggregated SGLang support and related CI/configs; consolidates MI355x runner to single-node path and updates GB200 Dynamo script.
dsr1-fp8-mi355x-sglang-disaggfromamd-master.yamlbenchmarks/dsr1_fp8_mi355x_sglang-disagg_slurm.shrunners/launch_mi355x-amd.shto single-nodesalloc/srun; drop multinode/disagg orchestration and log collectionperf-changelog.yamlbenchmarks/dsr1_fp8_gb200_dynamo-sglang_slurm.sh(env var checks, Dynamo clone/submit flow)Written by Cursor Bugbot for commit 5dd6a9b. This will update automatically on new commits. Configure here.