Remove fp16 kernels that have no public entry point#268
Merged
rapids-bot[bot] merged 4 commits intorapidsai:branch-24.08from Aug 1, 2024
Merged
Remove fp16 kernels that have no public entry point#268rapids-bot[bot] merged 4 commits intorapidsai:branch-24.08from
rapids-bot[bot] merged 4 commits intorapidsai:branch-24.08from
Conversation
tfeher
added
bug
benfred
approved these changes
Jul 31, 2024
cjnolet
requested changes
Jul 31, 2024
Contributor
Author
|
Moving comments from PR description here: Supporting FP16 is beneficial for decreasing memory footprint of large dataset, therefore it is planned to revert this PR in the future and add the missing interfaces. #264 adds the missing pieces to run vector search with FP16 data, but it comes with ~ 50 MB increase in binary size:
It is somewhat surprising that we have so large binary size increase, all these components shall be just thin wrappers around functions compiled in separate object files. |
Contributor
Author
|
/merge |
divyegala
pushed a commit
to divyegala/cuvs
that referenced
this pull request
Aug 7, 2024
`libcuvs.so` contains fp16 kernels that are not accessible (missing headers and missing public entry points). This PR removes the unused kernel. Authors: - Tamas Bela Feher (https://github.com/tfeher) Approvers: - Ben Frederickson (https://github.com/benfred) - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#268
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
libcuvs.socontains fp16 kernels that are not accessible (missing headers and missing public entry points). This PR removes the unused kernel.