NVIDIA AI
@NVIDIAAI
Teaching your AI new tricks.
参加 June 2016
855 フォロー中 294.8K ファン
What if every decode step gave the next one a head start?
Meet Guess-Verify-Refine — a new hardware-aware sparse-attention algorithm from NVIDIA Research. Built for TensorRT LLM on Blackwell, it reuses temporal patterns across decode steps for:
→ 1.88x faster Top-K attention
→ 9.3% better end-to-end latency in low-latency serving
Dive into the paper:
もっと見る
