# Performance

> Browse 32 items tagged with Performance.

## Items

- [VectorDBBench](https://vectordb.ever.works/items/vectordbbench-benchmarking-tool) — An open-source benchmarking tool from Zilliz for comparing vector database performance and cost-effectiveness. Provides an intuitive visual interface to reproduce results and test new systems with standardized metrics.
- [Vector Database Performance Benchmark 2026](https://vectordb.ever.works/items/vector-database-performance-benchmark-2026) — Comprehensive benchmark dataset comparing 10 vector databases across 19 fields including query latency (p50/p99), throughput, scalability limits, features like hybrid search and ACID compliance, SDK support, and managed pricing. Tested with 1M vectors at 1536 dimensions for RAG and AI search applications. Key highlights include Qdrant for lowest latency, Pinecone for managed scalability, and pgvector for ACID transactions.
- [VectorDBBench](https://vectordb.ever.works/items/vectordbbench) — Open-source vector database benchmarking tool testing databases across production-critical scenarios including static collection, filtering, and streaming cases with modern embedding model datasets.
- [Qdrant Vector Search Benchmarks](https://vectordb.ever.works/items/qdrant-vector-search-benchmarks) — Open-source comparative benchmarks evaluating vector search performance of engines like Qdrant, Elasticsearch, Milvus, Redis, and Weaviate. Covers single-node upload/search, filtered search across various datasets and configurations, focusing on RPS, latency, precision, and indexing time using affordable hardware.
- [LeanVec: Search Your Vectors Faster by Making Them Fit](https://vectordb.ever.works/items/leanvec-search-your-vectors-faster-by-making-them-fit) — Research paper introducing LeanVec, a technique to accelerate vector search by reducing vector dimensionality while preserving search accuracy. Published as an arXiv preprint in 2023 by Mariano Tepper et al.
- [Early Termination Strategy for HNSW](https://vectordb.ever.works/items/early-termination-strategy-for-hnsw) — Optimization technique that allows HNSW vector searches to exit early when the candidate queue remains saturated, reducing latency and resource usage with minimal recall impact.
- [Exploring Distributed Vector Databases Performance on HPC Platforms](https://vectordb.ever.works/items/exploring-distributed-vector-databases-performance-on-hpc-platforms) — SC'25 Workshop paper characterizing Qdrant vector database performance on high-performance computing platforms, bridging AI and HPC workloads.
- [The Novel Vector Database](https://vectordb.ever.works/items/the-novel-vector-database) — Research paper proposing a decoupled storage architecture for vector databases that improves update speed by 10.05x for insertions and 6.89x for deletions through innovative design.
- [VectorDBBench Leaderboard](https://vectordb.ever.works/items/vectordbbench-leaderboard) — Public benchmark leaderboard comparing vector database performance across multiple cloud and open-source solutions with standardized testing scenarios for production workloads.
- [GridStore](https://vectordb.ever.works/items/gridstore) — Qdrant's custom-built storage engine written in Rust, replacing RocksDB with improved performance and lower latency for payload and sparse vector storage.
- [Lazy Loading Filesystem](https://vectordb.ever.works/items/lazy-loading-filesystem) — Modal Labs' FUSE-based filesystem implementation that loads container images and dependencies on-demand, enabling sub-second container startup times for GPU workloads.
- [Embedding API Latency](https://vectordb.ever.works/items/embedding-api-latency) — The time required to generate vector embeddings from text, images, or other data via API calls or local inference. Embedding latency significantly impacts RAG system performance, with typical ranges from 10ms (local, batch) to 500ms+ (API, single) depending on model size and deployment.
- [Vector Index Rebuild Strategies](https://vectordb.ever.works/items/vector-index-rebuild-strategies) — Approaches for updating vector database indexes when data changes significantly, including zero-downtime rebuilds, incremental updates, and blue-green deployments. Index rebuilds are necessary when adding large batches of vectors, changing parameters, or optimizing performance in production systems.
- [Vector Index Types](https://vectordb.ever.works/items/vector-index-types) — Different indexing strategies for vector databases including HNSW, IVF, LSH, and flat indexes. Each type offers different trade-offs between query speed, build time, accuracy, and memory usage. Understanding index types is crucial for optimizing vector database performance at scale.
- [Vector Search Caching](https://vectordb.ever.works/items/vector-search-caching) — Strategies for caching vector search results, embeddings, and frequently accessed data to reduce latency and costs in RAG systems. Effective caching can eliminate redundant embedding API calls and vector searches for common queries, significantly improving performance and reducing infrastructure costs.
- [Semantic Caching](https://vectordb.ever.works/items/semantic-caching-embeddings) — A caching technique that uses vector embeddings to identify and reuse responses for semantically similar queries, reducing LLM costs and latency. Unlike traditional caches based on exact matches, semantic caching achieves cache hit ratios of up to 92% by matching queries based on semantic similarity.
- [LLM Caching for Vector Search](https://vectordb.ever.works/items/llm-caching-for-vector-search) — Caching strategies for LLM and vector search systems including semantic caching, embedding caching, and response caching to reduce costs and improve latency in RAG applications.
- [Retrieval Metrics](https://vectordb.ever.works/items/retrieval-metrics) — Performance measurement framework for vector search and RAG systems including recall, precision, nDCG, MRR, and context relevance metrics to evaluate retrieval quality and relevance.
- [Vector Database Benchmarking](https://vectordb.ever.works/items/vector-database-benchmarking) — Comprehensive guide to benchmarking vector databases covering performance testing methodologies, standard benchmarks like ANN-Benchmarks, and best practices for evaluating throughput, latency, and accuracy.
- [Vector Database Performance Tuning](https://vectordb.ever.works/items/vector-database-performance-tuning) — Best practices and techniques for optimizing vector database performance including index selection, quantization strategies, query optimization, and hardware considerations for production deployments.
- [ANN Algorithm Complexity Analysis](https://vectordb.ever.works/items/ann-algorithm-complexity-analysis) — Computational complexity comparison of approximate nearest neighbor algorithms including build time, query time, and space complexity. Essential for understanding performance characteristics and choosing appropriate algorithms for different scales.
- [Consistency Levels](https://vectordb.ever.works/items/consistency-levels) — Configuration options in distributed vector databases that trade off between data consistency, availability, and performance. Critical for understanding read/write behavior in production systems with replication.
- [Cursor-Based Pagination](https://vectordb.ever.works/items/cursor-based-pagination) — A pagination technique for efficiently scrolling through large vector database result sets using cursors instead of offsets. Essential for retrieving all vectors in a collection or iterating through search results without performance degradation.
- [Vector Index Build Strategies](https://vectordb.ever.works/items/vector-index-build-strategies) — Techniques for efficiently building vector indexes including batch construction, incremental updates, and online indexing. Critical for production systems that need to balance indexing speed, search performance, and resource utilization.
- [Vector Query Optimization](https://vectordb.ever.works/items/vector-query-optimization) — Techniques for optimizing vector search queries including parameter tuning, result caching, batch queries, and index selection. Critical for achieving production-grade performance and cost efficiency.
- [GPTCache (Semantic Cache)](https://vectordb.ever.works/items/gptcache-semantic-cache) — Open-source semantic caching library for LLMs that uses embedding similarity to identify and retrieve responses for similar queries, reducing API costs by up to 70% and improving response times for ChatGPT and other language models.
- [RAPIDS cuVS](https://vectordb.ever.works/items/rapids-cuvs) — GPU-accelerated vector search library from NVIDIA providing approximate nearest neighbors and clustering algorithms with up to 12x faster index builds and 4.7x lower search latency through GPU parallelization.
- [Vector Database Performance Tuning Guide](https://vectordb.ever.works/items/vector-database-performance-tuning-guide) — Comprehensive guide covering index optimization, quantization, caching, and parameter tuning for vector databases. Includes techniques for balancing performance, cost, and accuracy at scale.
- [Photon Engine](https://vectordb.ever.works/items/photon-engine) — A general-purpose analytical engine with built-in vector processing capabilities, excelling at traditional analytical workloads and efficient handling of vector operations. It is an example of a vector engine.
- [Milvus Sizing Tool](https://vectordb.ever.works/items/milvus-sizing-tool) — Milvus Sizing Tool helps users estimate the hardware and resource requirements needed to deploy Milvus based on their anticipated data scale and workload.
- [MyScale's Vector Database Benchmark](https://vectordb.ever.works/items/myscales-vector-database-benchmark) — Benchmark results and tools by MyScale aimed at measuring the performance of vector databases in various search and retrieval tasks.
- [Qdrant's Vector Database Benchmarks](https://vectordb.ever.works/items/qdrants-vector-database-benchmarks) — A set of benchmarks provided by Qdrant for evaluating vector databases, focusing on speed, scalability, and accuracy of vector search operations.

---

_Canonical page: https://vectordb.ever.works/tags/performance_