研究团队提出跨硬件优化框架ModelBlaster

1. 13:00
   arXiv 机器学习

   ModelBlaster：通过学习增强智能体跨模型、算子与硬件后端弥合性能差距

   ModelBlaster 提出内存增强上下文强化学习（MAIC-RL）框架，通过推理时更新知识库实现跨算子、模型与异构硬件的优化及经验复用。

Current heat 7·Comparable peak 10（Nov 4 14:00）·Comparable change, last 24 hours–

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.