Workflow
昇腾Atlas 800T A2设备
icon
Search documents
智谱联合华为开源图像生成模型 GLM-Image
GLM-Image是首个在国产芯片上完成全程训练的SOTA多模态模型,全流程均在昇腾Atlas 800T A2设备 上完成,验证了在国产全栈算力底座上训练前沿模型的可行性。 依托昇腾NPU和昇思MindSpore AI框架,使用动态图多级流水下发、高性能融合算子、多流并行等特 性,智谱自研了模型训练套件,全面优化数据预处理、预训练、SFT和后训练的端到端流程。通过动态 图的多级流水优化机制,将Host侧算子下发的关键阶段流水化并高度重叠,消除下发瓶颈;通过多流并 行策略,通信和计算互掩,打破文本梯度同步、图像特征广播等操作的通信墙,极致优化性能;使用 AdamW EMA、COC、RMS Norm等昇腾亲和的高性能融合算子,同步提升训练的稳定性和性能。 21世纪经济报道记者孔海丽 1月13日,智谱联合华为开源新一代图像生成模型GLM-Image,在科普插画、多格图画、社交媒体图 文、商业海报、写实摄影等方面均可落地。 近期,以Nano Banana Pro为代表的闭源图像生成模型正在推动图像生成与大语言模型的深度融合。技 术范式正从单一的图像生成,进化为兼具世界知识与推理能力的认知型生成,这些模型在海报、PPT ...
智谱(02513)联合华为开源首个国产芯片训练的多模态SOTA模型
智通财经网· 2026-01-14 00:33
Core Viewpoint - The collaboration between Zhiyu (02513) and Huawei has led to the launch of the new generation image generation model GLM-Image, marking a significant advancement in AI technology using domestic chips [1] Group 1: Model Development - GLM-Image is based on the Ascend Atlas 800T A2 device and the MindSpore AI framework, completing the entire training process from data to training [1] - It is the first state-of-the-art (SOTA) multimodal model fully trained on domestic chips [1] Group 2: Technological Innovation - The model employs an innovative "autoregressive + diffusion decoder" hybrid architecture, which integrates image generation with language models [1] - This development represents an important exploration for Zhiyu towards a new generation of "cognitive generation" technology paradigm, exemplified by the Nano Banana Pro [1]
智谱联合华为开源首个国产芯片训练的多模态SOTA模型
Ge Long Hui· 2026-01-14 00:31
Core Viewpoint - The collaboration between Zhiyuan and Huawei has led to the development of GLM-Image, a new generation image generation model that is the first SOTA multimodal model trained entirely on domestic chips [1] Group 1: Model Development - GLM-Image is based on the Ascend Atlas 800T A2 device and the MindSpore AI framework, completing the entire process from data to training [1] - The model employs an innovative "autoregressive + diffusion decoder" hybrid architecture, enabling the integration of image generation and language modeling [1] Group 2: Technological Significance - This development represents a significant exploration for Zhiyuan towards a new generation of "cognitive generation" technology paradigm, exemplified by the Nano Banana Pro [1]