PiPNN nearest-neighbor search wins three awards, up to 78x faster index building
khademinori · x · 2026-09-11
The PiPNN high-dimensional nearest-neighbor search framework won Best Paper at KDD'26, VecDB'26, and SISAP'26. The original work delivers an order-of-magnitude speedup for building navigable proximity graphs; an optimized kernel and GPU version push total speedup to 78x. NNS underpins data deduplication and embedding-driven RAG retrieval.
More from Infra
- Your p99 latency benchmark may be lying: a deep dive into coordinated omission — Franc0Fernand0 · 2026-09-11
- Running MiniMax H3 on 12GB VRAM: quantization, Turbo LoRAs and attention backends compared — Possible_Mood676 · 2026-09-11
- Spomin: live KV cache compaction squeezes 500k tokens of context into 180k resident — wgaca2 · 2026-09-11
- M.2-Oculink eGPU Link Silently Downgrades to PCIe Gen1 — Here's How to Check — El_90 · 2026-09-11
- DeepSeek launches V4.1-Flash with 1M-token context and 4x smaller KV-cache — matlabulous · 2026-09-11
- What Can You Still Run on 8GB VRAM? User Asks for Small Models With Tool Use — riceinmybelly · 2026-09-11