Iterative CAGRA-Q - #1810
Conversation
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
aamijar
added
non-breaking
… search - Configurable growth-phase in-build search params (itopk_size, search_width, max_iterations) and internal/smem dtype; itopk auto-forced on the final full-size iteration. - Decouple compression params used during iterative construction from the target index compression. - Add shuffle_dataset option; fix out-of-bounds access from the in-place raft gather by switching to an out-of-place gather.
…around) The shuffle_dataset path used an out-of-place gather into a temporary buffer to work around an illegal memory access in raft's in-place gather overload when n_rows * row_len exceeded 2^31 (32-bit index overflow). That bug is now fixed upstream in raft (NVIDIA/raft#3059, closes #3055), which the cuvs raft pin now includes. Revert to the in-place gather to drop the extra full-size temporary allocation and copy.
8fc10ac to
4f4068a
Compare
|
It looks like a lot of files were edited to change the copyright header? I think we should revert those. This commit 6ad9234 reverted minor diff in a test file. We should look through the merge conflicts due to Datasets API and resolve them. |
This reverts commit d9c6bfd.
…set on disk. Also added tests
…t to the algorithm as a path
…_dataset() is always true
…ches without the dense rows
achirkin
left a comment
achirkin
left a comment
There was a problem hiding this comment.
Please undo all changes to bench/ann/src/common. Let's keep CAGRA-Q compressed dataset support as before - by letting the compressed dataset be a part of index file / folder.
We should leave a proper refactoring of the benchmark harness for discussion and implementation in follow up work (if and how we want to pass compressed datasets as first-class input to the benchmarks).
I created a standalone PR for the vpq dataset serialisation. We can look through it and merge faster that this PR, and start working on the cuvsbench refactoring sooner. I need the refactoring to rerun the benchmarks (the older performance numbers are obsolete now). I won't be comfortable merging this PR into main before the new benchmarks land |
… graphs are already on the device
…ing the CAGRA-Q path
7 participants
Build CAGRA on PQ datasets with Iterative CAGRA-Q
Iterative cagra graph construction using CAGRA-Q search.
This PR improves the iterative CAGRA build method by enabling PQ compression: the dataset is compressed before the iterative search starts, and CAGRA-Q is used to iteratively update the KNN graph.
This is the first time we are introducing building CAGRA on (PQ) quantized datasets directly.