Models & Labs
Hugging Face Implements Agentic Resource Discovery
Hugging Face Bloghigh confidence
Why it matters
- →ARD enables dynamic discovery of AI capabilities, enhancing flexibility for developers.
- →It shifts from static catalogs to intent-based searches, improving scalability.
- →The open standard allows for broad industry adoption and integration.
Hugging Face has introduced the Agentic Resource Discovery (ARD) specification, developed in collaboration with Microsoft, Google, and others. ARD allows AI agents to dynamically search and discover capabilities at runtime, moving away from the traditional install-first model. The Hugging Face Discover Tool, a reference implementation of ARD, provides access to a vast array of AI skills and services. This initiative aims to create a more flexible and scalable ecosystem for AI agents, enabling them to find and utilize tools without prior configuration.
Read originalMore 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.