MB-72542: Fallback to CPU vector search if k > 2048 for a GPU index#429
Merged
Conversation
capemox
requested review from
CascadingRadium,
Likith101,
Samsonnyyeet,
Thejas-bhat,
Copilot,
maneuvertomars and
steveyen
Contributor
There was a problem hiding this comment.
Pull request overview
This PR prevents Faiss GPU vector searches from erroring when k exceeds the GPU implementation limit (2048) by explicitly falling back to the CPU index for large top‑k requests.
Changes:
- Introduces a
maxGPUSearchKconstant documenting Faiss GPU’s maximum supportedk. - Updates GPU index search routing to use GPU only when
k <= 2048(and no selector/params), otherwise falls back to CPU. - Clarifies fallback comment to include the “k too large” case.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
CascadingRadium
approved these changes
Jun 23, 2026
Likith101
approved these changes
Jun 23, 2026
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Faiss's GPU impl sets a max k value of 2048, and errors out for values higher than it. In case k is higher, the request falls back to the CPU index.