Models & Labs
Google Expands Gemini API with New Agent Features
Google AI Bloghigh confidence
Why it matters
- →Enhances developer ability to build autonomous agents with complex task handling.
- →Improves reliability and production readiness of AI applications.
- →Provides seamless integration with external tools and secure environments.
Google has announced new features for its Gemini API, enhancing Managed Agents with capabilities like background task execution and remote MCP server integration. These updates allow developers to build more autonomous agents that can perform complex tasks asynchronously, improving reliability and production readiness. The API now supports custom function calling and network credential refresh, ensuring seamless operation within a secure cloud sandbox. These enhancements make the Gemini API a more versatile tool for developers looking to create sophisticated AI agents.
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.