NVIDIA & SakanaAILabs Collaborate on ICML2026 Paper: Sparse Transformer Kernels Optimized for NVIDIA GPUs
NVIDIA AI(@NVIDIAAI)146 字 (约 1 分钟)
87
NVIDIA and SakanaAILabs co-author an ICML2026 paper introducing TwELL sparse packing and fused CUDA kernels, achieving >20% inference/training speedup at scale.
入选理由：TwELL稀疏打包格式可实现99%以上神经元稀疏度，对下游性能影响小于1%
FeaturedTweet#Transformer#Sparse Computing#NVIDIA GPU#LLM Optimization#ICML2026英文