Deepseek has announced the open-sourcing of DeepInfer, the inference engine that powers its latest AI model, V4.1-Flash. This vLLM-based system is designed to significantly lower compute costs and energy consumption when running AI models, a move that could intensify pricing competition among major AI providers, particularly OpenAI and Anthropic.
The release of DeepInfer is expected to democratize access to high-performance AI capabilities, enabling more developers and organizations to leverage advanced AI technology without incurring prohibitive costs. As the AI landscape evolves, this initiative may encourage further innovation and collaboration across the industry.
Compiled automatically by the Tech AI Newsdesk from public AI-news sources and summarised in our own words.
