Resolve Operator fallback to method allocator if temp alloc fails (#20981) (#20981) - #20981
Resolve Operator fallback to method allocator if temp alloc fails (#20981) (#20981)#20981rstehle wants to merge 1 commit into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20981
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 95028f7 with merge base 8a19761 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@rstehle has exported this pull request. If you are a Meta employee, you can view the originating Diff in D109855815. |
This PR needs a
|
…torch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: Andrew-github-user, rascani Differential Revision: D109855815
2da43a9 to
186e3df
Compare
…torch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: Andrew-github-user, rascani Differential Revision: D109855815
186e3df to
67aa6c0
Compare
|
/easycla |
1 similar comment
|
/easycla |
|
@rstehle has imported this pull request. If you are a Meta employee, you can view this in D109855815. |
| // is not provided (or an empty one is provided), we | ||
| // fall back to the method allocator. | ||
| if (allocator == nullptr || allocator->size() == 0) { | ||
| if (allocator == nullptr || allocator->size() == 0 || allocator->size() < (sizeof(TensorMeta) * n_args) + (sizeof(executorch::aten::DimOrderType) * kTensorDimensionLimit * n_args)) { |
There was a problem hiding this comment.
this line will probably fail the lintrunner.
c42c51c to
80baee5
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
80baee5 to
62a92fb
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
62a92fb to
13f4cb2
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
13f4cb2 to
6006632
Compare
|
@pytorchbot rerun -f |
|
❌ 🤖 pytorchbot command failed: Try |
|
@pytorchbot rerun -f "test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job" |
|
❌ 🤖 pytorchbot command failed: Try |
6006632 to
5eefb49
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
5eefb49 to
22c6167
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
22c6167 to
a85077f
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
886ae56 to
6397c3a
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
6397c3a to
fe1c699
Compare
|
@pytorchbot merge |
|
Mergebot is not configured for this repository. Please use the merge button provided by GitHub. |
fe1c699 to
3b945c7
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
3b945c7 to
18bee5b
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
18bee5b to
aa34c12
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
68dc1c4 to
b36c074
Compare
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
…torch#20981) (pytorch#20981) Summary: Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present. This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta. Reviewed By: rascani Differential Revision: D109855815 Pulled By: rstehle
b36c074 to
95028f7
Compare
Summary:
Currently, the resolve_operator step during method_init will fall back to method allocator if temp allocator is zero or not present.
This change adds logic to fallback to method allocator if temp allocator is present, but insufficient in size for the tensor meta.
Reviewed By: rascani
Differential Revision: D109855815
Pulled By: rstehle