| Large Language Model | LLM (Large Language Model) is an AI model trained on massive text data, capable of understanding and generating natural language, with a parameter scale typically ranging from billions to hundreds of billions. |
| Inference Service | Inference Service refers to a service in the field of machine learning or deep learning that provides high-performance, scalable prediction or inference capabilities for trained models. |
| Inference Runtimes | Inference Runtime provides a high-performance container environment for model-based inference services, optimizing resource utilization, accelerating the inference process, and reducing latency. |
| AI Agent | AI Agent is an AI entity that perceives its environment, makes decisions, and executes tasks autonomously, featuring autonomy, adaptability, and goal-orientation. |
| Text Generation | Text Generation refers to the process of automatically generating coherent and meaningful text content using Natural Language Processing (NLP) techniques, based on given inputs such as context, prompts, or rules. |
| Text Classification | Text Classification is the process of assigning text data to predefined categories or labels, typically achieved through machine learning or deep learning models, and used in various applications such as information retrieval, sentiment analysis, and spam detection. |
| Text-to-Image | Text-to-Image is the process of automatically generating images from input text descriptions using AI technology that combines NLP and computer vision to convert text into visual content. |
| Virtual GPU | Virtual GPU (vGPU) is a technology that leverages virtualization to split and allocate physical GPU resources to multiple virtual machines, enabling shared and efficient utilization of graphics processing capabilities. |
| Physical GPU | Physical GPU (pGPU) refers to the technology that directly attaches an entire physical GPU card on the host machine to a virtual machine for exclusive access to GPU resources. |
