docs: update vector benchmarks after insert optimization#273
Merged
Conversation
new numbers from GCP c2-standard-8 after binary VADD_BATCH encoding and parallel HNSW construction optimizations: - single key: 2,432 insert/sec (was 1,501), 1,217 query/sec - 8 shards: 5,482 insert/sec, 1,793 query/sec, p99=0.62ms - 4-6x less memory than all competitors (29 MB vs 139-178 MB) adds shard scaling table showing near-linear insert throughput scaling across shard counts.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
summary
updates vector benchmark numbers in README.md and bench/README.md with results from the binary encoding + parallel HNSW construction optimizations (#272).
new numbers from GCP c2-standard-8 (100k vectors, 128-dim, cosine, M=16, ef=64):
also adds a shard scaling table showing near-linear insert throughput scaling.
what was tested
benchmarks run on existing GCP c2-standard-8 VM with latest main (includes #272).