Use turbine for gen_sharktank imports. #1904
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
|
vk failure seems gen related |
yep, needed to set the jobs to use IMPORTER=1 as that's where shark-turbine is added to requirements |
88 tasks
monorimet
force-pushed
the
ean-turbine-gen
branch
from
edc4361 to
3be95a7
Compare
"windows not yet supported for torch.compile" blocks turbine gen from working in windows CI
|
nice.... I think I can use transformerbuilder for the dict_input models........ and leave the rest as aot.exports since it's so simple. when I have a chance we'll gut SHARK/tank and just use the turbine tests for most of the way |
|
Closing as model testing/validation will live in SHARK-Turbine |
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Outdated suggestions cannot be applied.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.
Needs these changes nod-ai/SHARK-ModelDev#102 for a successful run for certain models.
TODO: turbine integration for models that accept multiple inputs.
TODO: complete sets of artifacts for turbine path (needs hash generating for each .mlir)