Replace flatten with ravel to avoid unnecessary time cost of data copy #376
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
jokerz0624
force-pushed
the
improve_data_copy
branch
from
7b18c0d
to
89c2ae0
Compare
…cost of data copy
jokerz0624
force-pushed
the
improve_data_copy
branch
from
89c2ae0
to
093dbc7
Compare
|
@matthewkotila anyone here to review this change? |
|
Did you file a CLA with respect to https://github.com/triton-inference-server/server/blob/main/CONTRIBUTING.md? It looks fine to me |
GuanLuo
approved these changes
Dec 19, 2023
There was a problem hiding this comment.
LGTM. @jbkyang-nvi can you kick off a CI containing the change?
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Outdated suggestions cannot be applied.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.
When using shared memory mode, it's unnecessary to have a copy of input data by 'numpy. flatten()' .
'numpy. ravel()' is enough because then we just 'std::memcpy' it instead of modifying it.