NVIDIA Multi-GPU UMAP Processes 870GB of Data in Just 8 Minutes
leland_mcinnes · x · 2026-08-20
NVIDIA cuML and cuVS libraries now support multi-GPU execution for the UMAP algorithm. The new implementation partitions data into balanced clusters, computes local kNN graphs independently, and merges them, avoiding all-to-all communication. Tests on MIRACL and Wiki datasets showed up to a 74x speedup over projected CPU runtimes using eight H100 GPUs, making massive workloads feasible while preserving embedding quality.
Related event: NVIDIA Brings Multi-GPU UMAP, Processing 870GB in 8 Minutes(2 posts)→
More from Infra
- Data Center Developers Offer $4M for Virginia Homes to Build Campus — Polymarket · 2026-08-20
- Seeking Best Open Source Harness for Qwen3.8:27B on macOS — emax · 2026-08-20
- Optimizing AI Costs: Right-Sizing Intelligence Spend with Model Mixtures — iamrobotbear · 2026-08-20
- AWS AgentCore adds runtime domain and date filters for Web Search — AWS ML Blog · 2026-08-20
- AWS automates mortgage document processing, cutting time by 70% — AWS ML Blog · 2026-08-20
- AWS patterns for async agent calls in serverless pipelines — AWS ML Blog · 2026-08-20