introduce cuda stream into runtime backend #14903
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
This diff introduces CUDA streams into the Executorch runtime backend. The changes include: * Adding CUDA stream support to the `cuda_backend.cpp` file * Including the `cuda_runtime.h` header file in `cuda_backend.cpp` * Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream * Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false. Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/) [ghstack-poisoned]
Gasoonjia
requested review from
JacobSzwejbka,
lucylq and
swolchok
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14903
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 17 PendingAs of commit 2edb21a with merge base 0142a1a ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Oct 8, 2025
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
larryliu0820
reviewed
Oct 8, 2025
Comment on lines
184
to
197
|
|
||
| /** | ||
| * Check a condition and log an error message if the condition is false. | ||
| * | ||
| * @param[in] _condition The condition to check. | ||
| * @param[in] _format Log message format string. | ||
| */ | ||
| #define ET_CHECK_OR_LOG(_condition, _format, ...) \ | ||
| do { \ | ||
| if (!(_condition)) { \ | ||
| ET_LOG(Error, _format, ##__VA_ARGS__); \ | ||
| } \ | ||
| } while (0) | ||
|
|
There was a problem hiding this comment.
Make it explicit that we are logging at Error level. Maybe ET_CHECK_OR_LOG_ERROR? The other thing you can do is let this macro take a logging level.
larryliu0820
approved these changes
Oct 8, 2025
This diff introduces CUDA streams into the Executorch runtime backend. The changes include: * Adding CUDA stream support to the `cuda_backend.cpp` file * Including the `cuda_runtime.h` header file in `cuda_backend.cpp` * Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream * Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false. Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/) [ghstack-poisoned]
Gasoonjia
added a commit
that referenced
this pull request
Oct 8, 2025
Pull Request resolved: #14903 This diff introduces CUDA streams into the Executorch runtime backend. The changes include: * Adding CUDA stream support to the `cuda_backend.cpp` file * Including the `cuda_runtime.h` header file in `cuda_backend.cpp` * Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream * Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false. ghstack-source-id: 314914426 @exported-using-ghexport Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/)
This diff introduces CUDA streams into the Executorch runtime backend. The changes include: * Adding CUDA stream support to the `cuda_backend.cpp` file * Including the `cuda_runtime.h` header file in `cuda_backend.cpp` * Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream * Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false. Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/) [ghstack-poisoned]
Gasoonjia
added a commit
that referenced
this pull request
Oct 8, 2025
Pull Request resolved: #14903 This diff introduces CUDA streams into the Executorch runtime backend. The changes include: * Adding CUDA stream support to the `cuda_backend.cpp` file * Including the `cuda_runtime.h` header file in `cuda_backend.cpp` * Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream * Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false. ghstack-source-id: 314915602 @exported-using-ghexport Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/)
This diff introduces CUDA streams into the Executorch runtime backend. The changes include: * Adding CUDA stream support to the `cuda_backend.cpp` file * Including the `cuda_runtime.h` header file in `cuda_backend.cpp` * Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream * Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false. Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/) [ghstack-poisoned]
Gasoonjia
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
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.
Stack from ghstack (oldest at bottom):
This diff introduces CUDA streams into the Executorch runtime backend. The changes include:
cuda_backend.cppfilecuda_runtime.hheader file incuda_backend.cppvoid* cuda_streamfield to theAOTInductorModelContainerstruct inaoti_model_container.hto store the CUDA streamET_CHECK_OR_LOGinlog.hto check a condition and log an error message if the condition is false.Differential Revision: D84128173