[NVIDIA] chore: remove h200-trt runner type#185
Conversation
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
There was a problem hiding this comment.
Pull Request Overview
This PR removes the redundant h200-trt runner type label, consolidating all H200 runners under the single h200 label since both labels map to the same set of runner nodes.
- Removed
h200-trtentries from runner configuration and color mapping - Updated documentation and help text to reference
b200-trtinstead ofh200-trtas example - Modified workflow logic to eliminate duplicate
h200runner type generation
Reviewed Changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| utils/plot_perf.py | Removed h200-trt color mapping entry |
| utils/matrix-logic/generate_sweep_configs.py | Updated help text examples to use b200-trt instead of h200-trt |
| .github/workflows/full-sweep-test.yml | Simplified runner type logic to avoid duplicate h200 entries |
| .github/configs/runners.yaml | Removed the entire h200-trt runner type configuration |
| .github/configs/nvidia-master.yaml | Updated runner references from h200-trt to h200 |
| .github/configs/CONFIGS.md | Updated documentation example from h200-trt to b200-trt |
| .github/README.md | Updated example command to use b200-trt instead of h200-trt |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
The set of runners with label
h200is actually the same as the set of runners with labelh200-trt. So we can just remove theh200-trtlabel from all H200 runner nodes and remove from the codebase accordingly.Ran the following test sweep across runner type
h200and frameworktrt: https://github.com/InferenceMAX/InferenceMAX/actions/runs/19142142469https://github.com/InferenceMAX/InferenceMAX/actions/runs/19142146665
https://github.com/InferenceMAX/InferenceMAX/actions/runs/19142152143
Invoked by running the E2E Tests workflow with the command: