Models & Labs
Google I/O 2026: Gemini 3.5 and Omni Unveiled
Google AI Bloghigh confidence
Why it matters
- →Gemini 3.5 Flash offers high-speed intelligence, reducing development time and cost.
- →Gemini Omni enhances creative processes with its ability to generate content from any input.
- →These models make sophisticated AI tools more accessible to developers and creators.
Google announced major advancements at I/O 2026, including the launch of Gemini 3.5 Flash and Gemini Omni. Gemini 3.5 Flash offers high-speed intelligence, excelling in coding and agentic benchmarks, and is available through Google Antigravity and AI Studio. Gemini Omni, starting with video, can generate content from any input, enhancing realism with advanced physics understanding. These models aim to streamline complex tasks and creative processes, making AI tools more accessible and efficient for developers and creators.
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.