NVIDIA Integrates TriAttention: Trigonometric KV Compression for Long Context

青稞AI · wechat · 2026-08-20

To address the VRAM bottleneck of KV Cache in long reasoning, NVIDIA researchers proposed TriAttention. The method leverages the observation that pre-RoPE Q/K vectors cluster tightly around a fixed center. By approximating attention logits with trigonometric series based on this centrality, TriAttention effectively scores key importance for cache pruning. It has been merged into NVIDIA TensorRT-LLM and adopted by the LongLive video generation framework, reducing local-attention KV memory by 50% without quality loss.

Original post →

More from Infra

Infra channel →