e-means lands across tusKANNy stack, cutting vector index clustering training time by 1.5-5x
CShorten30 · x · 2026-11-20
- Meta researchers modernized k-means into e-means for 2026, and the tusKANNy ecosystem has integrated it across its vector search stack: Vectorium 0.12, kANNolo 0.17, and TACHIOM 0.7.
- Result: 1.5x-5x faster training at the same or lower clustering error.
- The ecosystem is touted as research-friendly and extensible: community contributor Robro612 wired e-means into kANNolo and TACHIOM indices, reporting a practically free speedup on index construction, with PR feedback from Silvio Martinico.
- For anyone doing vector search / ANN indexing, this is a low-cost performance improvement worth tracking.
More from Infra
- Liquid d1-2B decision model answers 19-30x more questions/min than same-size LLMs — mervenoyann · 2026-11-20
- Cactus Compute publishes 12 papers in 2026, 5 at NeurIPS, focused on on-device efficiency — joemeno · 2026-11-20
- Modular rebuilds MAX's Module API with PyTorch-like syntax and eager mode — clattner_llvm · 2026-11-20
- AWS Lambda doubles function timeout to 30 minutes for on-demand Event Functions — DavidWells · 2026-11-20
- Microsoft taps Intel EMIB packaging for Azure silicon, locks in Diamond Rapids supply — Beth_Kindig · 2026-11-20
- Polymarket puts DOJ criminally charging Nvidia this year at just 5% — Polymarket · 2026-11-20