Models & Labs
NVIDIA Unveils Cosmos 3 for Physical AI Development
NVIDIA Bloghigh confidence
Why it matters
- →Cosmos 3 enhances AI systems' ability to predict and act in real-world scenarios.
- →It provides developers with tools to generate synthetic data for training AI systems.
- →The model supports fine-tuning for specific tasks, improving AI adaptability.
NVIDIA has introduced Cosmos 3, a foundation model aimed at advancing physical AI systems, including robots and autonomous vehicles. Announced at NVIDIA GTC Taipei, Cosmos 3 combines vision reasoning with multimodal generation to help AI systems understand and predict real-world scenarios. It can generate action data necessary for robotic tasks, enhancing their ability to operate autonomously. This model supports developers in creating synthetic data and refining AI systems for specific tasks and environments. Cosmos 3's release is a notable development in making AI systems more responsive and effective in complex, dynamic settings.
Read originalMore from NVIDIA Blog
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.