Initial workflow file for gemm-sweep-analysis #42
Conversation
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
oyazdanb
reviewed
Dec 15, 2025
| channels: | ||
| description: 'Comma-separated NCCL channel values' | ||
| required: true | ||
| default: '28,42,56,70' |
Collaborator
There was a problem hiding this comment.
reduce it to 28 and 56 only
| gemm-sweep: | ||
| name: Run GEMM Sweep Profiling | ||
| runs-on: [self-hosted, gpu, rocm] | ||
| timeout-minutes: 180 |
Collaborator
There was a problem hiding this comment.
timeout-minutes seem high.
Collaborator
Author
There was a problem hiding this comment.
Please suggest an apropriate limit.
| docker exec ${{ env.CONTAINER_NAME }} bash -c " | ||
| bash scripts/gemm_analysis/run_train_various_channels.sh \ | ||
| --output-dir ${{ steps.setup.outputs.sweep_dir }} \ | ||
| --channels ${{ github.event.inputs.channels || '28,42,56,70' }} \ |
Collaborator
There was a problem hiding this comment.
reduce the number of channels to 28 and 56
| - name: Extract top GEMM kernels | ||
| run: | | ||
| # Parse channels and threads into space-separated format | ||
| CHANNELS=$(echo "${{ github.event.inputs.channels || '28,42,56,70' }}" | tr ',' ' ') |
oyazdanb
approved these changes
Dec 15, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This is an initial version of GH action for gemm-sweep analysis
Note : YML uses requirements.txt, but I have added this file in this review as it will cause conflict.
TODO :
Cretae rccl run action (rccl related changes are still on the way : Intergrate rccl changes into tracelense single config #41 )
Find out a way to dump comparing html
Need a runner machine and update the yml accordingly