[BE]Enhance _get_clean_triton.py to auto-generate launch_params if missing #154666
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
Added functionality to the process_file function to automatically generate the launch_params file if it does not exist and the auto_generate_params flag is set to True. This includes running the input file in a subprocess with the appropriate environment variable. Updated the get_clean_triton function and the main script to support this new feature, allowing users to disable auto-generation via a command-line argument.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/154666
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit cb05a8e with merge base 08fdc64 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
davidberard98
approved these changes
May 30, 2025
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
sorry, I didn't see your review comments for the nit. did you forget to save? |
nWEIdia
pushed a commit
to nWEIdia/pytorch
that referenced
this pull request
Jun 2, 2025
…ssing (pytorch#154666) Previously, @Chillee wrote a script pytorch#125811 to remove inductor dependency for inductor compiled triton kernels. We'd like to automate the process of obtaining the launch parameters. Added functionality to the torch/utils/_get_clean_triton.py to automatically generate the launch_params file if it does not exist and the auto_generate_params flag is set to True. This includes running the input file in a subprocess with the appropriate environment variable. Updated the get_clean_triton function and the main script to support this new feature, allowing users to disable auto-generation via a command-line argument. # Test Plan test embedding op in TritonBench ``` # generate inductor compiled triton kernels TORCH_COMPILE_DEBUG=1 TORCHINDUCTOR_FX_GRAPH_CACHE=0 python run.py --op embedding --mode fwd --precision fp32 --metrics nsys_rep --only inductor_embedding --num-inputs 1 --input-id 11 # run the script to get rid of inductor dependency. By default, triton_only_repro.py is the output file name. python ~/pytorch/torch/utils/_get_clean_triton.py ~/tritonbench/torch_compile_debug/run_2025_05_29_14_47_50_497790-pid_849274/torchinductor/model__0_forward_1.0/output_code.py ``` Pull Request resolved: pytorch#154666 Approved by: https://github.com/davidberard98
iupaikov-amd
pushed a commit
to ROCm/pytorch
that referenced
this pull request
Jun 4, 2025
…ssing (pytorch#154666) Previously, @Chillee wrote a script pytorch#125811 to remove inductor dependency for inductor compiled triton kernels. We'd like to automate the process of obtaining the launch parameters. Added functionality to the torch/utils/_get_clean_triton.py to automatically generate the launch_params file if it does not exist and the auto_generate_params flag is set to True. This includes running the input file in a subprocess with the appropriate environment variable. Updated the get_clean_triton function and the main script to support this new feature, allowing users to disable auto-generation via a command-line argument. # Test Plan test embedding op in TritonBench ``` # generate inductor compiled triton kernels TORCH_COMPILE_DEBUG=1 TORCHINDUCTOR_FX_GRAPH_CACHE=0 python run.py --op embedding --mode fwd --precision fp32 --metrics nsys_rep --only inductor_embedding --num-inputs 1 --input-id 11 # run the script to get rid of inductor dependency. By default, triton_only_repro.py is the output file name. python ~/pytorch/torch/utils/_get_clean_triton.py ~/tritonbench/torch_compile_debug/run_2025_05_29_14_47_50_497790-pid_849274/torchinductor/model__0_forward_1.0/output_code.py ``` Pull Request resolved: pytorch#154666 Approved by: https://github.com/davidberard98
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Previously, @Chillee wrote a script #125811 to remove inductor dependency for inductor compiled triton kernels. We'd like to automate the process of obtaining the launch parameters.
Added functionality to the torch/utils/_get_clean_triton.py to automatically generate the launch_params file if it does not exist and the auto_generate_params flag is set to True. This includes running the input file in a subprocess with the appropriate environment variable. Updated the get_clean_triton function and the main script to support this new feature, allowing users to disable auto-generation via a command-line argument.
Test Plan
test embedding op in TritonBench