You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2022/11/01 16:28:46 UTC

[GitHub] [tvm] yelite opened a new pull request, #13255: [MetaSchedule] Improve the script for TorchBench model tuning & benchmarking

yelite opened a new pull request, #13255:
URL: https://github.com/apache/tvm/pull/13255

   This PR adds features to the `python/tvm/meta_schedule/testing/torchbench/run.py`
   
   - Integrate with the TVM PyTorch integration to handle boolean tensor and unaligned memory.
   - Deduplicate collected tuning tasks to prevent thousands of tasks created by hundreds of subgraphs with similar structure.
   - Add option to cast model to float32, which are more stable numerically than float16 and prevents inaccurate result from many models.
   - Add option to choose search strategy in MetaSchedule.
   - Inspect output error if the actual output doesn't match the expectation. Also save the actual output and expected output for further analysis if needed.
   - Save subgraphs and their example input for debug purpose.
   - Print MetaSchedule profiling information at the end of execution.
   - Detach PyTorch tensor before exporting to dlpack.
   - Fix the sys path to avoid conflict with the `benchmarks` package installed by TorchBench dependency.
   - Trim all command line args passed in, in order to prevent breaking some TorchBench model that depends on args.
   - Empty cuda cache before starting the actual benchmark.
   
   cc: @junrushao @zxybazh 


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] junrushao merged pull request #13255: [MetaSchedule] Improve the script for TorchBench model tuning & benchmarking

Posted by GitBox <gi...@apache.org>.
junrushao merged PR #13255:
URL: https://github.com/apache/tvm/pull/13255


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] tvm-bot commented on pull request #13255: [MetaSchedule] Improve the script for TorchBench model tuning & benchmarking

Posted by GitBox <gi...@apache.org>.
tvm-bot commented on PR #13255:
URL: https://github.com/apache/tvm/pull/13255#issuecomment-1298795995

   <!---bot-comment-->
   
   Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @-ing them in a comment.
   
   <!--bot-comment-ccs-start-->
    * cc @Hzfengsy, @elvin-n, @junrushao <sub>See [#10317](https://github.com/apache/tvm/issues/10317) for details</sub><!--bot-comment-ccs-end-->
   
   <sub>Generated by [tvm-bot](https://github.com/apache/tvm/blob/main/ci/README.md#github-actions)</sub>


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org