PyNNDescent 0.7 slashes kNN-graph build times by an order of magnitude
leland_mcinnes · x · 2026-10-28
PyNNDescent 0.7 delivers major kNN-graph and index build speedups. On a 64-core Xeon 2.8GHz, MS MARCO (1M × 30,109) build time drops from 14,000s in v0.5 to single-digit seconds in v0.7, with RCV1 and NY Times similarly falling from thousands of seconds to tens; sparse-data builds go from hours to minutes.
Related event: PyNNDescent 0.7 Delivers Massive kNN Graph Speedups(4 posts)→
More from Infra
- 230 agent-run experiments on LLM inference: 8 lessons from DeepSeek 4.1 Flash tuning — jiayq · 2026-10-29
- Together's Post-Training Uses Per-GPU Pricing to Cut Agent Rollout Costs — togethercompute · 2026-10-29
- GitHub Unveils New Git Architecture Hitting 7,200 Writes/sec for AI Collaboration — mariorod1 · 2026-10-29
- NVIDIA CTO Michael Kagan on Mellanox, NVLink and Planet-Scale Computing — BenBajarin · 2026-10-29
- Indie researcher publishes SGTE, a from-scratch alternative inference architecture to beat the scaling wall — ReportProfessional57 · 2026-10-29
- HP and Asus shift some PC production back to China as AI drives up costs — pstAsiatech · 2026-10-29