Skip to content

[WIP] ANN Bench Wrapper Changes for Iterative CAGRA-Q - #2608

Draft
tarang-jain wants to merge 48 commits into
NVIDIA:mainfrom
tarang-jain:pr-1810-ann-bench
Draft

tarang-jain wants to merge 48 commits into
NVIDIA:mainfrom
tarang-jain:pr-1810-ann-bench

Conversation

@tarang-jain

Copy link
Copy Markdown
Contributor

cc @irina-resh-nvda
This was separated out from #1810.
Merge after #1810

irina-resh-nvda and others added 30 commits July 14, 2026 00:53
… 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.
…emporaries in iterative build (~2.7x faster build)
This reverts commit d9c6bfd.
@copy-pr-bot

copy-pr-bot Bot commented Sep 14, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants