Ant Group's CodeFuse Plugin for Development Assistant Releases New Version with Android Studio Support

The AntBlink R&D Assistant CodeFuse plugin has released a new version, adding support for Android Studio. This plugin is now compatible with 11 major IDEs, including Visual Studio Code, IDEA, and others. The new version has been optimized for front-end languages such as JavaScript and TypeScript, improving the accuracy of code completion, resulting in a 20% increase in adoption rate for front-end code generation compared to the old version. Additionally, new features include an entry for product inquiries with "R&D Xiaomi" and a logout function. Developers can apply for test qualifications on the official website to learn more about the plugin details.

Ant Group CodeFuse Open Source ModelCache for Large Model Semantic Caching

The ModelCache architecture under Ant Group's CodeFuse includes the adapter, embedding, similarity, and data_manager modules. ModelCache can reduce the inference cost of large model applications and enhance user experience. Cache hits can reduce average latency by 10 times, with speed improvements of up to 14.5%. ModelCache will continue to optimize performance and accuracy, improving recall time.

Ant Group Releases Open Source Code Model CodeFuse-CodeLlama-34B in 4bits Quantized Version

Ant Group has released the 4bits quantized version of CodeFuse-CodeLlama-34B. The quantized model can be loaded on a single A10 or RTX4090. The quantized model achieves a performance of 73.8% on the Humaneval pass@1 metric. CodeFuse is Ant's self-developed large model for code generation, aimed at enhancing developers' efficiency by providing intelligent suggestions and real-time support.

Qwen Code from Tongyi Qianwen Makes a Major Upgrade to v0.5.0! From Command-line Tool to a Full-scale Development Ecosystem

Tongyi Lab of Alibaba Cloud released the Qwen Code v0.5.0 version, upgrading the domestic AI programming tool from a command-line tool to a full-chain development ecosystem platform. The new version enhances core coding capabilities and breaks through plugin integration, engineering context understanding, and developer collaboration support, introducing a multi-tool collaborative architecture to build a developer's digital workspace.

Yuanbao X Huan Yuan 2025 Annual Report Released: Over 70% of Users Choose the Quick Thinking Mode

The 2025 report from the Yuanbao platform shows that the Huan Yuan model has achieved multi-dimensional upgrades in AI capabilities. The platform offers two modes: "Quick Thinking" and "Deep Thinking." Over 70% of users choose the "Quick Thinking" mode, with nearly half of the questions resolved in the first round. The "Deep Thinking" mode is suitable for complex scenarios, with dialogues usually lasting more than three rounds, and nearly half of them can generate multi-step structured content. In terms of image interaction, the Huan Yuan T1-Vis model was launched in May.

Ant Group's CodeFuse Plugin for Development Assistant Releases New Version with Android Studio Support

Related Recommendations

Ant Group CodeFuse Open Source ModelCache for Large Model Semantic Caching

Ant Group Releases Open Source Code Model CodeFuse-CodeLlama-34B in 4bits Quantized Version

Loomi, the World's First AI Influence Agent, Redefines Content Creation with IDE Thinking

Qwen Code from Tongyi Qianwen Makes a Major Upgrade to v0.5.0! From Command-line Tool to a Full-scale Development Ecosystem

Yuanbao X Huan Yuan 2025 Annual Report Released: Over 70% of Users Choose the Quick Thinking Mode