Models & Labs
NVIDIA and Hugging Face Enhance Robotics with New Models
NVIDIA Bloghigh confidence
Why it matters
- →This collaboration democratizes access to advanced robotics tools for developers.
- →It fosters innovation by providing standardized models and frameworks for robot development.
- →The integration supports the open robotics community in advancing physical AI capabilities.
NVIDIA and Hugging Face have announced a collaboration to integrate NVIDIA's advanced robotics models and frameworks into Hugging Face's open source library, LeRobot. This includes the NVIDIA Isaac GR00T 1.7 model and the Isaac Teleop framework, which will provide developers with standardized tools for robot development. The partnership aims to make robotics development more accessible and collaborative by offering shared models and workflows. An upcoming addition, the NVIDIA Cosmos 3 model, will further enhance capabilities for data generation and simulation in robotics.
Read originalMore from NVIDIA Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.