Models & Labs
Google unveils Gemini 3.5 and Omni at I/O 2026
Google AI Bloghigh confidence
Why it matters
- →Gemini 3.5 and Omni represent a leap in AI's ability to handle complex tasks and create content.
- →These models could redefine user interaction with technology, making AI more integral to daily life.
- →Google's advancements may set new standards for AI capabilities in various industries.
At Google I/O 2026, Google announced the launch of Gemini 3.5 and Gemini Omni, marking a new era in AI capabilities. Gemini Omni can generate high-quality videos from a mix of images, audio, and text, while Gemini 3.5 focuses on executing complex workflows. These advancements aim to make AI more proactive and integrated into users' daily lives. The announcements highlight Google's commitment to pushing the boundaries of AI technology and its applications.
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.