Faster KNN index builds in Manticore
Manticore can now build KNN indexes in parallel when saving chunks, merging chunks, and rebuilding KNN data. On a 16-core machine, building a KNN index for 1M vectors dropped from 8 minutes to 39 seconds.
Sharding in Manticore Search: automatic distribution and replication
How sharding works in Manticore Search, from splitting a table across CPU cores on a single node to automatic multi-node distribution that maintains a replication factor on its own.
14× faster embeddings: how we rebuilt the ONNX path in Manticore
Released in Manticore Search 27.1.5, the new ONNX Runtime backend makes auto-embeddings ~14× faster on average than the previous SentenceTransformers/Candle path on the same hardware, same model, same weights — and the margin holds whether you run 1 client thread or 32.
Manticore Search under systemd: beyond fork, PID files, and guesswork
Run Manticore Search under systemd with accurate status reporting, cleaner reloads, journal-based logging, and safer shutdowns for RT workloads.
Faster KNN search in Manticore: 2-pass HNSW, batched distances, and AVX-512
Three optimizations that speed up HNSW vector search by up to 29%: restructured graph traversal for better cache utilization, batched distance computations, and AVX-512 support.
Manticore Search 27.1.5: Authentication, sharded tables, conversational search and faster vector search
Manticore Search 27.1.5 adds built-in authentication and authorization, introduces sharded tables, add conversational search, speeds up vector search, improves faceting and aggregations, and includes 65 fixes since 25.0.0.
