Models & Labs
Nvidia Unveils AI Agent-Centric Tech at COMPUTEX
The Rundown AIhigh confidence
Why it matters
- →Nvidia's focus on AI agents could shift how compute resources are utilized.
- →The introduction of advanced models and processors positions Nvidia as a leader in AI technology.
- →This strategy highlights the growing importance of autonomous systems in tech infrastructure.
Nvidia has unveiled a series of new AI technologies at COMPUTEX 2026, emphasizing the role of AI agents in future computing. The company introduced the RTX Spark chips, designed to run AI agents on PCs, and the Vera processor, which outperforms rivals in task completion. Additionally, Nvidia launched the Cosmos 3 robotics model and the Nemotron 3 Ultra model, highlighting its comprehensive approach to AI development. This move underscores Nvidia's strategy to prioritize AI agents as key consumers of compute power, potentially reshaping the tech landscape.
Read originalMore from The Rundown AI
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.
