A single DISKANN graph stored in a distributed key-value store, with an in-memory head index and near-data scoring, serves 50B vectors at 100k+ QPS with higher recall than partitioned serving.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DISTRIBUTEDANN: Efficient Scaling of a Single DISKANN Graph Across Thousands of Computers
A single DISKANN graph stored in a distributed key-value store, with an in-memory head index and near-data scoring, serves 50B vectors at 100k+ QPS with higher recall than partitioned serving.