Add dot product computation between two quantized vectors#37250
Merged
Conversation
This is more efficient than explicitly dequantizing the vectors (and then running a float32 dot product) since it does not involve any inverse rotations. Vectors must have been quantized using the _logically_ same quantizer, using `InnerProduct` mode. Same `const`-ness/thread-safety caveats apply as other quantizer functions due to the current need for scratch space for unpacking of bits.
havardpe
approved these changes
Jun 19, 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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
@havardpe please review
This is more efficient than explicitly dequantizing the vectors (and then running a float32 dot product) since it does not involve any inverse rotations. Vectors must have been quantized using the logically same quantizer and using
InnerProductmode for the output to make sense.Same
const-ness/thread-safety caveats apply as other quantizer functions due to the current need for scratch space for unpacking of bits.