[MPS] Fix testing for generator operators #137601
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
Before this changes, tests for operators like `eye` or `triu_indices` were essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the same Moved the logic to `transform_opinfo_sample_to_mps` whicih in addition to copying tensors is also tweaks `kwargs` [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/137601
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 cc5a89c with merge base de4c2a3 ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
pytorch-bot
bot
added
ciflow/mps
Before this changes, tests for operators like `eye` or `triu_indices` were essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the same Moved the logic to `transform_opinfo_sample_to_mps` whicih in addition to copying tensors is also tweaks `kwargs` [ghstack-poisoned]
Before this changes, tests for operators like `eye` or `triu_indices` were essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the same Moved the logic to `transform_opinfo_sample_to_mps` whicih in addition to copying tensors is also tweaks `kwargs` Discovered that: - `torch.randn` and `torch.randint` fall into the same undefined category - `torch.logspace` is not implemented for MPS - `torch.linspace` is not implemented for bfloat16 (fix is coming) and integral dtypes - `torch.triu_indices` are not implemented (PR is coming, this is how I've discovered this problem) [ghstack-poisoned]
Before this changes, tests for operators like `eye` or `triu_indices` were essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the same Moved the logic to `transform_opinfo_sample_to_mps` whicih in addition to copying tensors is also tweaks `kwargs` Discovered that: - `torch.randn` and `torch.randint` fall into the same undefined category - `torch.logspace` is not implemented for MPS - Allow 1.0 absolute tolerance for all `torch.linspace` calls over integral input as rounding is wrong on the MPS side - `torch.triu_indices` are not implemented (PR is coming, this is how I've discovered this problem) [ghstack-poisoned]
Before this changes, tests for operators like `eye` or `triu_indices` were essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the same Moved the logic to `transform_opinfo_sample_to_mps` whicih in addition to copying tensors is also tweaks `kwargs` Discovered that: - `torch.randn` and `torch.randint` fall into the same undefined category - `torch.logspace` is not implemented for MPS - Allow 1.0 absolute tolerance for all `torch.linspace` calls over integral input as rounding is wrong on the MPS side - `torch.triu_indices` are not implemented (PR is coming, this is how I've discovered this problem) - `torch.signal.windows.kaiser` fails because `aten::i0` is not implemented [ghstack-poisoned]
This was referenced Oct 9, 2024
Before this changes, tests for operators like `eye` or `triu_indices` were essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the same Moved the logic to `transform_opinfo_sample_to_mps` whicih in addition to copying tensors is also tweaks `kwargs` Discovered that: - `torch.randn` and `torch.randint` fall into the same undefined category - `torch.logspace` is not implemented for MPS - Allow 1.0 absolute tolerance for all `torch.linspace` calls over integral input as rounding is wrong on the MPS side - `torch.triu_indices` are not implemented (PR is coming, this is how I've discovered this problem) - `torch.signal.windows.kaiser` fails because `aten::i0` is not implemented [ghstack-poisoned]
Contributor
Author
|
@pytorchbot merge -f "Lint + MPS tests are green" |
Collaborator
Merge startedYour change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
pytorchmergebot
pushed a commit
that referenced
this pull request
Oct 10, 2024
As for the most part those helper method need access to only base class methods. Also replace spurious `at::` namespace prefixes, i.e. `at::Tensor`->`Tensor` Pull Request resolved: #137647 Approved by: https://github.com/Skylion007, https://github.com/albanD ghstack dependencies: #137601
pytorchmergebot
pushed a commit
that referenced
this pull request
Oct 10, 2024
Requested in #77764 (comment) Copy-n-paste kernel implementation from https://github.com/pytorch/pytorch/blob/13cf8360d87306ab3242e827eb662682cff17a19/aten/src/ATen/native/cuda/TensorFactories.cu#L92 though use `float` instead of `double` for square root computation Pull Request resolved: #137648 Approved by: https://github.com/Skylion007, https://github.com/albanD ghstack dependencies: #137601, #137647
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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):
tri[lu]_indices#137648Tensor->TensorBasein OperationUtils.h #137647Before this changes, tests for operators like
eyeortriu_indiceswere essentially a test that respective CPU operators are stable, as cpu_sample and mps_sample were the sameMoved the logic to
transform_opinfo_sample_to_mpswhicih in addition to copying tensors is also tweakskwargsDiscovered that:
torch.randnandtorch.randintfall into the same undefined categorytorch.logspaceis not implemented for MPStorch.linspacecalls over integral input as rounding is wrong on the MPS sidetorch.triu_indicesare not implemented (PR is coming, this is how I've discovered this problem)torch.signal.windows.kaiserfails becauseaten::i0is not implemented