Update dlpack to version 0.8 #15237
Merged
Update dlpack to version 0.8 #15237
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
dantegd
added
libcudf
galipremsagar
approved these changes
Mar 5, 2024
robertmaynard
approved these changes
Mar 6, 2024
raydouglass
approved these changes
Mar 6, 2024
|
/merge |
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Outdated suggestions cannot be applied.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.
cuVS Python and Rust APIS use
dlpack0.8 to calllibcuvs. To be able to create a RAPIDS environment that has both cuDF and cuVS (and eventually cuML and other libraries where we will usedlpackas we do in cuVS) we require to update dlpack to match.PR notes:
There is 1 key relevant differences to RAPIDS between 0.5 and 0.8: support of
DLDeviceTypefor managed memory withkDLCUDAManagedWe don't currently require to update the existing libcudf to work with this, but this could be a useful addition that I would suggest exploring post 24.04.DLpack 1.0 release candidate was released recently with the key addition being adding versioning support in
DLManagedTensorVersioned.Given the timing for cuDF burndown, I think we should pin to 0.8 for 24.04 reducing the number of changes (which AFAIK all changes are non breaking so we shouldn't need code updates, pending CI testing), and then update cuDF/cuVS/etc. to use
DLManagedTensorVersionedonce dlpack 1.0 final version is released.cc @divyegala @cjnolet