Explore the latest AI trends, tech insights, and project updates
Stay updated with shenwenAI's latest developments
We are excited to announce the official release of shenwenAI 2.0! This update brings a brand-new model architecture, faster inference speeds, and lower resource consumption, delivering a more powerful local AI experience for developers.
Read MoreDive deep into the technical architecture and design philosophy of swllm.cpp. This article covers how we achieve efficient LLM inference through C/C++, along with implementation details of quantization optimization and hardware acceleration.
Read MoreThe shenwenAI team shares their thoughts and outlook on the future of open-source artificial intelligence. We believe that through community collaboration and technological innovation, everyone can access powerful AI capabilities, driving the democratization of technology.
Read More