mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-07-10 01:38:44 +00:00
feb4ee2753
* perf(hnsw): 4-accumulator AVX-512 kernels + SIMD wiring into search hot path - Replace single-accumulator AVX-512 distance kernels with 4-accumulator versions in simd_intrinsics.rs (euclidean, cosine, dot, manhattan). On Zen 5 with 4-cycle FMA latency, single-accumulator was latency-bound (96 cycles for 384-dim); 4-accumulator hides this to ~24 cycles. - Wire HNSW search hot path in DistanceFn::eval to call simd_intrinsics directly (inline, no Result wrapping, no simsimd FFI overhead). - Enable parallel batch insert via hnsw_rs::parallel_insert_slice (rayon). Measured: 6-10% QPS improvement on 128-dim/1K-vector bench; larger gains expected on 1M-vector workloads where distance computation dominates. 228 unit tests pass. Co-Authored-By: claude-flow <ruv@ruv.net> Claude-Session: https://claude.ai/code/session_019rVRYrRDKyxYK18kuVrDSf * perf(hnsw): gate parallel_insert_slice behind 10K-vector threshold Rayon-based parallel insert (hnsw_rs::parallel_insert_slice) degrades graph connectivity for small batches (<10K vectors) because worker threads can't see each other's in-flight insertions, reducing optimal neighbor links. Add PARALLEL_THRESHOLD=10_000: use parallel insert only when the batch is large enough that the graph quality converges. Below threshold: sequential insert_data (same as before this PR). Above threshold: parallel_insert_slice for build-time speedup. 228 unit tests pass. Co-Authored-By: claude-flow <ruv@ruv.net> Claude-Session: https://claude.ai/code/session_019rVRYrRDKyxYK18kuVrDSf * bench(sift1m): add SIFT-1M fvecs benchmark + hnswlib comparison tooling Adds two benchmark binaries driven by the real TEXMEX SIFT-1M dataset: * crates/ruvector-sota-bench/src/bin/sift1m_bench.rs Reads sift_base.fvecs / sift_query.fvecs / sift_groundtruth.ivecs directly (no HDF5 required). Sweeps ef_search to produce a recall@10 vs QPS table used for before/after PR #619 comparison. * scripts/sift1m_hnswlib_bench.mjs Same sweep via hnswlib-node (C++ HNSW) to measure the competitive gap. Cargo.toml: add simd-avx512 feature to sota-bench dependency so the full optimised kernel path is exercised. Measured on AMD Ryzen 9 9950X (Zen 5, AVX-512), M=16, efC=200, 1M vecs: Source Build ef=100 recall ef=100 QPS ef=200 recall ef=200 QPS before PR 849 s 0.9585 1,849 0.9713 1,058 after PR (#619) 774 s 0.9592 1,768 0.9722 1,024 hnswlib-node 322 s 0.9828 5,339 0.9957 2,897 Build speedup: +9.7 %. Query QPS at 1M-scale: within noise (memory- bandwidth bound, not compute-bound). Co-Authored-By: claude-flow <ruv@ruv.net> Claude-Session: https://claude.ai/code/session_019rVRYrRDKyxYK18kuVrDSf * style: cargo fmt for sift1m benchmark binary Co-Authored-By: claude-flow <ruv@ruv.net> Claude-Session: https://claude.ai/code/session_019rVRYrRDKyxYK18kuVrDSf --------- Co-authored-by: ruvnet <ruvnet@gmail.com>
61 lines
2.1 KiB
JSON
61 lines
2.1 KiB
JSON
{
|
|
"name": "ruvector",
|
|
"version": "0.1.2",
|
|
"description": "High-performance Rust-native vector database with AgenticDB compatibility",
|
|
"private": true,
|
|
"workspaces": [
|
|
"crates/ruvector-node",
|
|
"crates/ruvector-wasm",
|
|
"crates/ruvector-graph-node",
|
|
"crates/ruvector-graph-wasm"
|
|
],
|
|
"scripts": {
|
|
"build": "cargo build --release",
|
|
"build:node": "cd crates/ruvector-node && npm run build",
|
|
"build:wasm": "cd crates/ruvector-wasm && npm run build",
|
|
"build:graph": "npm run build:graph-node && npm run build:graph-wasm",
|
|
"build:graph-node": "cd crates/ruvector-graph-node && napi build --platform --release",
|
|
"build:graph-wasm": "cd crates/ruvector-graph-wasm && bash build.sh",
|
|
"build:all": "npm run build && npm run build:node && npm run build:wasm && npm run build:graph",
|
|
"test": "cargo test --workspace",
|
|
"test:graph": "cargo test -p ruvector-graph --all-features",
|
|
"test:integration": "cargo test --test graph_full_integration",
|
|
"bench": "cargo bench -p ruvector-bench",
|
|
"bench:graph": "cargo bench -p ruvector-graph",
|
|
"cli": "cargo run -p ruvector-cli --",
|
|
"mcp": "cargo run -p ruvector-cli --bin ruvector-mcp",
|
|
"example:graph": "cargo run --example simple_graph -p ruvector-graph",
|
|
"example:cypher": "cargo run --example cypher_queries -p ruvector-graph",
|
|
"example:hybrid": "cargo run --example hybrid_search -p ruvector-graph",
|
|
"example:distributed": "cargo run --example distributed_setup -p ruvector-graph --features distributed",
|
|
"lint": "cargo clippy --workspace -- -D warnings",
|
|
"format": "cargo fmt --all",
|
|
"check": "cargo check --workspace",
|
|
"check:graph": "cargo check -p ruvector-graph --all-features"
|
|
},
|
|
"keywords": [
|
|
"vector",
|
|
"database",
|
|
"embeddings",
|
|
"rust",
|
|
"hnsw",
|
|
"agentic",
|
|
"ai"
|
|
],
|
|
"license": "MIT",
|
|
"repository": {
|
|
"type": "git",
|
|
"url": "https://github.com/ruvnet/ruvector.git"
|
|
},
|
|
"engines": {
|
|
"node": ">=18.0.0"
|
|
},
|
|
"overrides": {
|
|
"axios": "^1.13.2",
|
|
"body-parser": "^2.2.1"
|
|
},
|
|
"dependencies": {
|
|
"@claude-flow/memory": "^3.0.0-alpha.7",
|
|
"hnswlib-node": "^3.0.0"
|
|
}
|
|
}
|