-
Notifications
You must be signed in to change notification settings - Fork 24.7k
BC fix for AOTIModelPackageLoader() constructor defaults #149082
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/149082
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit c6d633b with merge base b90698f ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
The default value for `run_single_threaded` was wrongly specified in the .cpp file instead of the header, breaking C++-side instantiation of `AOTIModelPackageLoader` with no arguments. This PR fixes this and adds a test for the use case of running with `AOTIModelPackageLoader` instead of `AOTIMo 8000 delContainerRunner` on the C++ side. cc desertfire chenyang78 penguinwu yushangdi benjaminglass1 [ghstack-poisoned]
The default value for `run_single_threaded` was wrongly specified in the .cpp file instead of the header, breaking C++-side instantiation of `AOTIModelPackageLoader` with no arguments. This PR fixes this and adds a test for the use case of running with `AOTIModelPackageLoader` instead of `AOTIModelContainerRunner` on the C++ side. cc desertfire chenyang78 penguinwu yushangdi benjaminglass1 [ghstack-poisoned]
xref #148601 |
@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 |
Merge failedReason: 1 jobs have failed, first few of them are: inductor / cuda12.6-py3.10-gcc9-sm86 / test (inductor_huggingface, 1, 1, linux.g5.4xlarge.nvidia.gpu) Details for Dev Infra teamRaised by workflow job |
@pytorchbot merge -i |
Merge startedYour change will be merged while ignoring the following 1 checks: inductor / cuda12.6-py3.10-gcc9-sm86 / test (inductor_huggingface, 1, 1, linux.g5.4xlarge.nvidia.gpu) Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Hi, @jbschlosser , @desertfire should we cherry-pick this fix to release 2.7? Without this fix, the example code in https://github.com/pytorch/pytorch/blob/main/docs/source/torch.compiler_aot_inductor.rst is getting compilation error:
|
@pytorchbot cherry-pick --onto release/2.7 -c regression |
@etaf yes that's the plan :) |
The default value for `run_single_threaded` was wrongly specified in the .cpp file instead of the header, breaking C++-side instantiation of `AOTIModelPackageLoader` with no arguments. This PR fixes this and adds a test for the use case of running with `AOTIModelPackageLoader` instead of `AOTIModelContainerRunner` on the C++ side. Pull Request resolved: #149082 Approved by: https://github.com/desertfire (cherry picked from commit 5e1b715)
Cherry picking #149082The cherry pick PR is at #149214 and it is recommended to link a regression cherry pick PR with an issue. The following tracker issues are updated: Details for Dev Infra teamRaised by workflow job |
BC fix for AOTIModelPackageLoader() constructor defaults (#149082) The default value for `run_single_threaded` was wrongly specified in the .cpp file instead of the header, breaking C++-side instantiation of `AOTIModelPackageLoader` with no arguments. This PR fixes this and adds a test for the use case of running with `AOTIModelPackageLoader` instead of `AOTIModelContainerRunner` on the C++ side. Pull Request resolved: #149082 Approved by: https://github.com/desertfire (cherry picked from commit 5e1b715) Co-authored-by: Joel Schlosser <jbschlosser@meta.com>
Stack from ghstack (oldest at bottom):
The default value for
run_single_threaded
was wrongly specified in the .cpp file instead of the header, breaking C++-side instantiation ofAOTIModelPackageLoader
with no arguments. This PR fixes this and adds a test for the use case of running withAOTIModelPackageLoader
instead ofAOTIModelContainerRunner
on the C++ side.cc @desertfire @chenyang78 @penguinwu @yushangdi @benjaminglass1