Add xfail tests for single layer Flux transformer that verify IREE results against Torch #741
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
sogartar
force-pushed
the
flux-transformer-run-with-iree
branch
from
9919b51 to
6f48e48
Compare
KyleHerndon
approved these changes
Jan 3, 2025
…sults against Torch The test accuracy is not of sufficient quality and needs further investigation. The tests compare IREE bf16 and f32 against Torch f32. Refactor the sample input generation and make it produce noise images for final size of 1024x1024 instead of 512x512.
sogartar
force-pushed
the
flux-transformer-run-with-iree
branch
from
92d8f52 to
88037f4
Compare
sogartar
added a commit
to sogartar/sharktank
that referenced
this pull request
Jan 3, 2025
Tests introuced by nod-ai#741 would actually hang during IREE compilation without one pending fix.
sogartar
added a commit
that referenced
this pull request
Jan 3, 2025
Tests introduced by #741 would actually hang during IREE compilation without one pending fix.
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
…sults against Torch (#741) The test accuracy is not of sufficient quality and needs further investigation. The tests compare IREE bf16 and f32 against Torch f32. Refactor the sample input generation and make it produce noise images for final size of 1024x1024 instead of 512x512. Remove unused duplicated function for random Theta generation.
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
Tests introduced by #741 would actually hang during IREE compilation without one pending fix.
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
…sults against Torch (#741) The test accuracy is not of sufficient quality and needs further investigation. The tests compare IREE bf16 and f32 against Torch f32. Refactor the sample input generation and make it produce noise images for final size of 1024x1024 instead of 512x512. Remove unused duplicated function for random Theta generation.
monorimet
pushed a commit
that referenced
this pull request
Jan 8, 2025
Tests introduced by #741 would actually hang during IREE compilation without one pending fix.
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.
The test accuracy is not of sufficient quality and needs further investigation.
The tests compare IREE bf16 and f32 against Torch f32.
Refactor the sample input generation and make it produce noise images for final size of 1024x1024 instead of 512x512.
Remove unused duplicated function for random Theta generation.