Small and Mighty: NVIDIA Accelerates Microsoft’s Open Phi-3 Mini Language Models
原文英文，约500词，阅读约需2分钟。发表于：。NVIDIA announced today its acceleration of Microsoft’s new Phi-3 Mini open language model with NVIDIA TensorRT-LLM, an open-source library for optimizing large language model inference when running on NVIDIA GPUs from PC to Cloud. Phi-3 Mini packs the capability of 10x larger models and is licensed for both research and broad commercial usage, advancing Phi-2 Read Article
NVIDIA加速了Microsoft的Phi-3 Mini开放语言模型，并使用NVIDIA TensorRT-LLM进行优化。Phi-3 Mini具有10倍大模型的能力，可用于研究和商业用途。Phi-3 Mini有两个变体，一个支持4k tokens，另一个支持128K tokens。开发者可以在ai.nvidia.com上尝试Phi-3 Mini，并在Jetson AI Lab上学习部署。TensorRT-LLM将支持Phi-3 Mini的长上下文窗口，并提供多种优化和内核。NVIDIA是开源生态系统的积极贡献者，并与Microsoft合作加速DirectML、Azure云、生成AI研究、医疗和生命科学等创新。
