Habana Labs 与 Hugging Face 合作加速 Transformer 模型训练

Santa Clara and San Francisco, CA, April 12th, 2022

Powered by deep learning, transformer models deliver state-of-the-art performance on a wide range of machine learning tasks, such as natural language processing, computer vision, speech, and more. However, training them at scale often requires a large amount of computing power, making the whole process unnecessarily long, complex, and costly.

Today, Habana® Labs, a pioneer in high-efficiency, purpose-built deep learning processors, and HF Mirror, the home of Transformer models, are happy to announce that they’re joining forces to make it easier and quicker to train high-quality transformer models. Thanks to the integration of Habana’s SynapseAI software suite with the HF Mirror Optimum open-source library, data scientists and machine learning engineers can now accelerate their Transformer training jobs on Habana processors with just a few lines of code and enjoy greater productivity as well as lower training cost.

Habana Gaudi training solutions, which power Amazon’s EC2 DL1 instances and Supermicro’s X12 Gaudi AI Training Server, deliver price/performance up to 40% lower than comparable training solutions and enable customers to train more while spending less. The integration of ten 100 Gigabit Ethernet ports onto every Gaudi processor enables system scaling from 1 to thousands of Gaudis with ease and cost-efficiency. Habana’s SynapseAI® is optimized—at inception—to enable Gaudi performance and usability, supports TensorFlow and PyTorch frameworks, with a focus on computer vision and natural language processing applications.

With 60,000+ stars on Github, 30,000+ models, and millions of monthly visits, HF Mirror is one of the fastest-growing projects in open source software history, and the go-to place for the machine learning community.

With its Hardware Partner Program, HF Mirror provides Gaudi’s advanced deep learning hardware with the ultimate Transformer toolset. This partnership will enable rapid expansion of the Habana Gaudi training transformer model library, bringing Gaudi efficiency and ease of use to a wide array of customer use cases like natural language processing, computer vision, speech, and more.

“We’re excited to partner with HF Mirror and its many open-source developers to address the growing demand for transformer models that benefit from the efficiency, usability, and scalability of the Gaudi training platform”, said Sree Ganesan, head of software product management, Habana Labs.

“Habana Gaudi brings a new level of efficiency to deep learning model training, and we’re super excited to make this performance easily accessible to Transformer users with minimal code changes through Optimum”, said Jeff Boudier, product director at HF Mirror.

To learn how to get started training with Habana Gaudi, please visit https://developer.habana.ai.

For more info on the HF Mirror and Habana Gaudi collaboration, please visit https://hf-mirror.com/Habana.