[TorchToLinalg] address a dtype mismatch in aten.multinomial lowering
#3630
Conversation
This file contains 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
zjgarvey
force-pushed
the
multinomial_patch
branch
from
dbfb527 to
b9a4e38
Compare
|
Huh, I don't even know what to say about a torchscript numerics mismatch... |
double causes onnx numerics failure, float32 causes linalg numerics failure
|
This is frustrating. Perhaps we should be using the TestUtils-generated sample args for the torchscript onnx export?? Neither zeros nor ones work uniformly for all tests. |
zjgarvey
force-pushed
the
multinomial_patch
branch
2 times, most recently
from
7fc400a to
102a01c
Compare
zjgarvey
force-pushed
the
multinomial_patch
branch
from
102a01c to
e969376
Compare
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Outdated suggestions cannot be applied.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.
Resolves #3628
Unblocks a compile failure for one of the MiGraphx models (
AgentModel).