
Tencent’s Weixin Integrates Ray for Large-Scale AI Deployment
In a significant move to enhance its AI capabilities, Tencent’s Weixin has announced the integration of Ray, an open-source distributed computing engine, into their infrastructure. This partnership aims to tackle the challenges of deploying large-scale AI systems efficiently and cost-effectively.
According to sources, the Weixin team faced numerous technical hurdles in handling computationally intensive tasks, such as Optical Character Recognition (OCR), which require over a million CPU cores. Their existing infrastructure, P6n platform, proved costly and complex for large-scale deployments, while the Gemini platform fell short in meeting real-time performance needs.
To overcome these challenges, Weixin developed AstraRay, a new AI compute engine built on Ray. This innovative solution addresses cost efficiency, high throughput, and reduced deployment complexity, enabling scalable AI deployment across heterogeneous resources.
Source: Blockchain.News