Running 8M-Point UMAP on a Single RTX 5090
enjalot · x · 2026-07-11
The author showcases the results of running parametric UMAP on 8 million data points using a single RTX 5090, and plans to push the limit to 16 million, with an ultimate goal of hitting 150 million points.
This is more of an engineering milestone share for large-scale embedding/visualization computing. The focus isn't on releasing a new model, but rather on scaling up data processing capabilities on a single GPU.
More from Infra
- China’s AI arms race is increasingly defined by chips, data centers, and open models — BenBajarin · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- Gavin Baker argues Nvidia may be one of open source AI’s biggest supporters — GavinSBaker · 2026-07-22
- AI Power Demand Exposes US Energy Gap, Urging Shift from Scarcity to Abundance — bradneuberg · 2026-07-22
- Gavin Baker says Nvidia’s $630B figure would be system revenue, not all Nvidia’s — GavinSBaker · 2026-07-22
- A Firecracker-based platform says it can host 6,000 AI agents on one 256 GB server — maritime_sh · 2026-07-22