[autotuner] Add default do_bench for CPU hosts #6570
Merged
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
Jokeren
reviewed
Apr 23, 2025
python/triton/runtime/autotuner.py
Outdated
|
|
||
| if do_bench is None: | ||
| self.do_bench = driver.active.get_benchmarker() | ||
| import torch |
Contributor
There was a problem hiding this comment.
I don't think this is the ideal solution. Maybe we could query if there's any backend exists and just set do_bench = None if no backend is available
Contributor
Author
There was a problem hiding this comment.
Thanks for taking a look. I updated V2 to lazily initialize do_bench. Could you please see if that looks good?
Jokeren
reviewed
Apr 23, 2025
Jokeren
approved these changes
Apr 24, 2025
Jokeren
requested changes
Apr 24, 2025
Jokeren
approved these changes
Apr 24, 2025
10 tasks
FindHao
pushed a commit
to FindHao/triton
that referenced
this pull request
Apr 30, 2025
<!--- The core Triton is a small number of people, and we receive many PRs (thank you!). To help us review your code more quickly, **if you are a new contributor (less than 3 PRs merged) we ask that you complete the following tasks and include the filled-out checklist in your PR description.** Complete the following tasks before sending your PR, and replace `[ ]` with `[x]` to indicate you have done them. --> # New contributor declaration - [x] I am not making a trivial change, such as fixing a typo in a comment. - [x] I have written a PR description following these [rules](https://cbea.ms/git-commit/#why-not-how). - [x] I have run `pre-commit run --from-ref origin/main --to-ref HEAD`. - Select one of the following. - [x] I have added tests. - `/test` for `lit` tests - `/unittest` for C++ tests - `/python/test` for end-to-end tests - [ ] This PR does not need a test because `FILL THIS IN`. - Select one of the following. - [ ] I have not added any `lit` tests. - [x] The `lit` tests I have added follow these [best practices](https://mlir.llvm.org/getting_started/TestingGuide/#filecheck-best-practices), including the "tests should be minimal" section. (Usually running Python code and using the instructions it generates is not minimal.) Fixes triton-lang#6150. When running on a CPU host, `triton.autotune()` throws an error: ``` RuntimeError: 0 active drivers ([]). There should only be one. ``` This issue was introduced by triton-lang#4496, which forces the caller to specify `do_bench`. But this may not be easy in a large codebase. Default `do_bench` to `triton.testing.do_bench` when there's no GPU. Add a unit test.
weiji14
added a commit
to weiji14/staged-recipes
that referenced
this pull request
Apr 30, 2025
Until patch triton-lang/triton#6570 is available in a new triton release.
weiji14
added a commit
to weiji14/staged-recipes
that referenced
this pull request
Aug 14, 2025
Since patch from triton-lang/triton#6570 is out in triton=3.4.0 on conda-forge now.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
New contributor declaration
I am not making a trivial change, such as fixing a typo in a comment.
I have written a PR description following these
rules.
I have run
pre-commit run --from-ref origin/main --to-ref HEAD.Select one of the following.
/testforlittests/unittestfor C++ tests/python/testfor end-to-end testsFILL THIS IN.Select one of the following.
littests.littests I have added follow these best practices,including the "tests should be minimal" section. (Usually running Python code
and using the instructions it generates is not minimal.)
Fixes #6150.
When running on a CPU host,
triton.autotune()throws an error:This issue was introduced by #4496,
which forces the caller to specify
do_bench. But this may not be easy in alarge codebase.
Default
do_benchtotriton.testing.do_benchwhen there's no GPU. Add aunit test.