Models & Labs
Gemini Robotics 2 Enhances Robot Intelligence
Google DeepMindhigh confidence
Why it matters
- →Gemini Robotics 2 enables robots to perform complex tasks with enhanced dexterity and whole-body control.
- →The system allows for quick adaptation to new environments and collaboration with other robots.
- →This development could significantly impact industries by providing more intelligent and adaptable robotic solutions.
Google DeepMind has unveiled Gemini Robotics 2, an advanced intelligence layer for robots that enhances their ability to perform complex tasks with whole-body control and dexterity. This new system allows robots to adapt to new environments and collaborate with other robots, significantly improving their task efficiency. Gemini Robotics 2 includes three models: a vision-language-action model, an embodied reasoning model, and an on-device model optimized for local operation. These advancements could revolutionize the integration of robots into various industries by providing more adaptable and intelligent robotic solutions.
Read originalMore from Google DeepMind
More in Models & Labs
Models & Labsmodels
Llama.cpp b10208 Release Enhances SYCL Performance
The latest b10208 release of llama.cpp introduces significant improvements in SYCL performance, particularly with the addition of oneMKL GEMM flash attention for XMX-accelerated prompt processing. This update addresses previous issues with interleaved destination layouts in the normalize kernel, ensuring more accurate attention outputs across models. By removing redundant stream waits and refining MKL FA dispatch gates, the release optimizes processing speeds, nearly doubling performance in some cases. These enhancements make llama.cpp a more robust and efficient tool for developers working with large language models.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10211 Release Expands Platform Support
The latest b10211 release of llama.cpp continues its trend of broadening platform compatibility, making it a versatile tool for developers across various systems. Notably, this update includes support for Ubuntu with ROCm 7.2, enhancing performance for AMD GPU users. Windows users benefit from the inclusion of CUDA 12 and 13 DLLs, ensuring compatibility with the latest NVIDIA technologies. While the release doesn't introduce new model architectures, it solidifies llama.cpp's position as a flexible inference runtime across diverse hardware configurations.