Skip to content

Iterative cagra q#1810

Open
irina-resh-nvda wants to merge 8 commits into
NVIDIA:mainfrom
irina-resh-nvda:iterative_cagra_q
Open

Iterative cagra q#1810
irina-resh-nvda wants to merge 8 commits into
NVIDIA:mainfrom
irina-resh-nvda:iterative_cagra_q

Conversation

@irina-resh-nvda

Copy link
Copy Markdown
Contributor

A draft PR for iterative cagra graph construction using cagra q search

@copy-pr-bot

copy-pr-bot Bot commented Feb 16, 2026

Copy link
Copy Markdown

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.

… 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.
@irina-resh-nvda irina-resh-nvda marked this pull request as ready for review July 15, 2026 08:48
@irina-resh-nvda irina-resh-nvda requested review from a team as code owners July 15, 2026 08:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature request New feature or request non-breaking Introduces a non-breaking change

Projects

Status: In Progress

Development

Successfully merging this pull request may close these issues.

4 participants