Paper: GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
AK(@_akhaliq)43 字 (约 1 分钟)
75
This paper proposes a new method using language models to predict GPU kernel runtime performance, demonstrating superior results compared to traditional methods in multiple benchmarks.
入选理由：论文提出 GPU Forecasters 方法，使用语言模型预测 GPU 内核性能。
FeaturedTweet#GPU#Language Model#Performance Optimization#AI#Computational Acceleration英文