Enable CAGRA index building without adding dataset to the index #2126
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
tfeher
added
improvement
tfeher
commented
Jan 24, 2024
| @@ -296,7 +296,8 @@ index<T, IdxT> build( | |||
| std::optional<experimental::nn_descent::index_params> nn_descent_params = std::nullopt, | |||
| std::optional<float> refine_rate = std::nullopt, | |||
| std::optional<ivf_pq::index_params> pq_build_params = std::nullopt, | |||
| std::optional<ivf_pq::search_params> search_params = std::nullopt) | |||
| std::optional<ivf_pq::search_params> search_params = std::nullopt, | |||
| bool construct_index_with_dataset = true) | |||
There was a problem hiding this comment.
Currently only cagra::detail::build is changed. This is enough to unblock benchmarking with RAFT-ANN-Bench, but ideally we should have such an option in the public API. Opinions?
tfeher
changed the title
tfeher
force-pushed
the
cagra_build_without_adding_dataset
branch
from
4fc8723 to
707547a
Compare
cjnolet
approved these changes
Feb 1, 2024
cjnolet
approved these changes
Feb 1, 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Outdated suggestions cannot be applied.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.
We can build a CAGRA graph even for datasets that do not fit GPU mem. The IVF-PQ build method only requires that the temporary IVF-PQ index (that we use for creating the knn-graph) fits the GPU. But once the CAGRA graph is constructed, we try to initialize the CAGRA index which would copy the dataset to device memory.
This PR adds a build flag, that would disable copying the dataset into the index. That enables building CAGRA graph for large datasets, and also allows users to customize allocator used for storing the data.