Make torch.library.triton_op public #141880
Closed
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/141880
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 2270bdb with merge base 9012e7a ( UNSTABLE - The following job failed but was likely due to flakiness present on trunk and has been marked as unstable:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
We've been using it privately for half a year and everything's been good. This PR: 1. Makes torch.library.triton_op public 2. Renames capture_triton -> wrap_triton. We got feedback that no one knew what "capture triton" does. 3. Makes torch.library.wrap_triton public. triton_op is used to construct a Python custom operator that may call 1+ triton kernels. Each of those triton kernels must be annotated with wrap_triton. Test Plan: - existing tests [ghstack-poisoned]
We've been using it privately for half a year and everything's been good. This PR: 1. Makes torch.library.triton_op public 2. Renames capture_triton -> wrap_triton. We got feedback that no one knew what "capture triton" does. 3. Makes torch.library.wrap_triton public. triton_op is used to construct a Python custom operator that may call 1+ triton kernels. Each of those triton kernels must be annotated with wrap_triton. Test Plan: - existing tests cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy yf225 chenyang78 kadeng muchulee8 ColinPeppler amjames desertfire chauhang aakhundov [ghstack-poisoned]
albanD
reviewed
Dec 2, 2024
| "register_vmap", | ||
| "get_ctx", | ||
| "custom_op", | ||
| "triton_op", |
There was a problem hiding this comment.
I can't find the doc being rendered for these on the website. Am I missing something ?
There was a problem hiding this comment.
Weird, let me dig into it
There was a problem hiding this comment.
@albanD they're in the preview of the PR that is one up in the stack (https://docs-preview.pytorch.org/pytorch/pytorch/141883/library.html). I don't know why they're not in this PR's doc preview
There was a problem hiding this comment.
RIP my browser cached the artifacts. If your browser does too then I'd recommend opening the docs page in incognito mode lol
There was a problem hiding this comment.
This is weird because putting triton_op in the search doesn't bring it up.
cc @svekars is that due to the new search? This sounds bad?
There was a problem hiding this comment.
This is weird because putting triton_op in the search doesn't bring it up. cc @svekars is that due to the new search? This sounds bad?
The search goes to stable docs most likely (the indexed pages). I will add a PR to enable old search in docs.preview.
We've been using it privately for half a year and everything's been good. This PR: 1. Makes torch.library.triton_op public 2. Renames capture_triton -> wrap_triton. We got feedback that no one knew what "capture triton" does. 3. Makes torch.library.wrap_triton public. triton_op is used to construct a Python custom operator that may call 1+ triton kernels. Each of those triton kernels must be annotated with wrap_triton. Test Plan: - existing tests cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy yf225 chenyang78 kadeng muchulee8 ColinPeppler amjames desertfire chauhang aakhundov [ghstack-poisoned]
pytorchmergebot
pushed a commit
that referenced
this pull request
Dec 3, 2024
Fixes #141618 Pull Request resolved: #141883 Approved by: https://github.com/albanD ghstack dependencies: #141894, #141880
pobin6
pushed a commit
to pobin6/pytorch
that referenced
this pull request
Dec 5, 2024
We've been using it privately for half a year and everything's been good. This PR: 1. Makes torch.library.triton_op public 2. Renames capture_triton -> wrap_triton. We got feedback that no one knew what "capture triton" does. 3. Makes torch.library.wrap_triton public. triton_op is used to construct a Python custom operator that may call 1+ triton kernels. Each of those triton kernels must be annotated with wrap_triton. Test Plan: - existing tests Pull Request resolved: pytorch#141880 Approved by: https://github.com/albanD ghstack dependencies: pytorch#141894
pobin6
pushed a commit
to pobin6/pytorch
that referenced
this pull request
Dec 5, 2024
) Fixes pytorch#141618 Pull Request resolved: pytorch#141883 Approved by: https://github.com/albanD ghstack dependencies: pytorch#141894, pytorch#141880
AmdSampsa
pushed a commit
to AmdSampsa/pytorch
that referenced
this pull request
Dec 9, 2024
We've been using it privately for half a year and everything's been good. This PR: 1. Makes torch.library.triton_op public 2. Renames capture_triton -> wrap_triton. We got feedback that no one knew what "capture triton" does. 3. Makes torch.library.wrap_triton public. triton_op is used to construct a Python custom operator that may call 1+ triton kernels. Each of those triton kernels must be annotated with wrap_triton. Test Plan: - existing tests Pull Request resolved: pytorch#141880 Approved by: https://github.com/albanD ghstack dependencies: pytorch#141894
AmdSampsa
pushed a commit
to AmdSampsa/pytorch
that referenced
this pull request
Dec 9, 2024
) Fixes pytorch#141618 Pull Request resolved: pytorch#141883 Approved by: https://github.com/albanD ghstack dependencies: pytorch#141894, pytorch#141880
Esquains
pushed a commit
to Esquains/study1
that referenced
this pull request
Dec 15, 2024
We've been using it privately for half a year and everything's been good. This PR: 1. Makes torch.library.triton_op public 2. Renames capture_triton -> wrap_triton. We got feedback that no one knew what "capture triton" does. 3. Makes torch.library.wrap_triton public. 4. Improves some typing. triton_op is used to construct a Python custom operator that may call 1+ triton kernels. Each of those triton kernels must be annotated with wrap_triton. Test Plan: - existing tests ghstack-source-id: a56bbd8 Pull Request resolved: pytorch/pytorch#141880
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Stack from ghstack (oldest at bottom):
We've been using it privately for half a year and everything's been
good. This PR:
knew what "capture triton" does.
triton_op is used to construct a Python custom operator that may call 1+
triton kernels. Each of those triton kernels must be annotated with
wrap_triton.
Test Plan:
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @chauhang @aakhundov