最新文章

共 129 篇

4GB GPU运行Llama3 70B：AirLLM框架让高端AI触手可及

This article demonstrates how to run the powerful Llama3 70B open-source LLM on just 4GB GPU memory using the AirLLM framework, making cutting-edge AI technology accessible to users with limited hardware resources. (本文展示了如何利用AirLLM框架，在仅4GB GPU内存的条件下运行强大的Llama3 70B开源大语言模型，使硬件资源有限的用户也能接触前沿AI技术。)

AI大模型2026/1/24

阅读全文 →

AirLLM：单卡4GB显存运行700亿大模型，革命性轻量化框架

AirLLM is an innovative lightweight framework that enables running 70B parameter large language models on a single 4GB GPU through advanced memory optimization techniques, significantly reducing hardware costs while maintaining performance. (AirLLM是一个创新的轻量化框架，通过先进的内存优化技术，可在单张4GB GPU上运行700亿参数的大语言模型，大幅降低硬件成本的同时保持性能。)

AI大模型2026/1/24

阅读全文 →

OpenBMB：清华大学开源社区如何推动大语言模型高效计算与参数微调

OpenBMB is an open-source community and toolset initiated by Tsinghua University since 2018, focused on building efficient computational tools for large-scale pre-trained language models. Its core contribution includes parameter-efficient fine-tuning methods, and it has released significant projects like UltraRAG 2.1, UltraEval-Audio v1.1.0, and the 4-billion-parameter AgentCPM-Explore model, which demonstrate strong performance in benchmarks. (OpenBMB是清华大学自2018年起支持发起的开源社区与工具集，致力于构建大规模预训练语言模型的高效计算工具。其核心贡献包括参数高效微调方法，并发布了UltraRAG 2.1、UltraEval-Audio v1.1.0和40亿参数的AgentCPM-Explore模型等重要项目，在多项基准测试中表现出色。)

AI大模型2026/1/24

阅读全文 →

OpenBMB开源AI新突破：MiniCPM系列与UltraRAG v3框架引领高效AI开发

UltraRAG v3 is a low-code MCP framework designed for building complex and innovative RAG pipelines, enabling efficient development with minimal coding requirements. (UltraRAG v3是一个低代码MCP框架，专为构建复杂创新的RAG管道而设计，能以最少的编码需求实现高效开发。)

AI大模型2026/1/24

阅读全文 →

FlashMLA：DeepSeek为Hopper GPU打造的高性能注意力解码内核

FlashMLA is an optimized MLA decoding kernel for Hopper GPUs that significantly improves LLM inference efficiency through advanced attention mechanisms and memory optimization. (FlashMLA是专为Hopper GPU优化的MLA解码内核，通过先进的注意力机制和内存优化显著提升大语言模型推理效率。)

DeepSeek2026/1/24

阅读全文 →

深度学习新突破：基于Transformer的光场视图生成模型

This article explores a novel deep learning model for generating light field views, detailing its neural architecture, training methodology, and applications in computational photography and VR. The model leverages transformer-based attention mechanisms to synthesize high-fidelity multi-view images from sparse inputs, addressing key challenges in angular consistency and computational efficiency. (本文探讨了一种用于生成光场视图的新型深度学习模型，详细介绍了其神经架构、训练方法以及在计算摄影和VR中的应用。该模型利用基于Transformer的注意力机制，从稀疏输入中合成高保真多视图图像，解决了角度一致性和计算效率方面的关键挑战。)

AI大模型2026/1/24

阅读全文 →

ILIAS平台AI安全漏洞深度解析：2024年教育技术风险应对指南

This analysis examines critical AI security vulnerabilities within the ILIAS Learning Management System, highlighting potential risks in data processing, model integrity, and access control mechanisms. The report provides technical insights for security professionals to identify, assess, and mitigate these vulnerabilities in educational technology environments. // 本分析深入探讨ILIAS学习管理系统中的关键AI安全漏洞，重点关注数据处理、模型完整性和访问控制机制中的潜在风险。报告为安全专业人员提供技术见解，帮助识别、评估和缓解教育技术环境中的这些漏洞。

AI大模型2026/1/24

阅读全文 →

新型技术解析：从定义到应用前景指南

This article introduces a novel deep learning model for generating light field views, which enhances 3D scene reconstruction and immersive visual experiences by simulating multi-perspective light information. The model leverages neural networks to predict light rays from sparse inputs, enabling applications in virtual reality, computational photography, and autonomous systems. (本文介绍了一种新型的深度学习模型，用于生成光场视图，通过模拟多视角光线信息来增强三维场景重建和沉浸式视觉体验。该模型利用神经网络从稀疏输入中预测光线，可应用于虚拟现实、计算摄影和自主系统等领域。)

AI大模型2026/1/24

阅读全文 →

新型深度学习模型：2024年光场视图生成技术突破与应用指南

This article explores a novel deep learning model for generating light field views, discussing its technical architecture, advantages over traditional methods, and potential applications in fields like virtual reality and medical imaging. (本文探讨了一种用于生成光场视图的新型深度学习模型，详细介绍了其技术架构、相较于传统方法的优势以及在虚拟现实、医学成像等领域的应用潜力。)

AI大模型2026/1/24

阅读全文 →