
NVIDIA has released the Nemotron 3 Ultra, a 550 billion parameter AI model available on Ollama's cloud platform. Designed for long-running agentic workflows, it features a 1 million token context to handle extensive codebases and research trails. The model uses NVFP4, a 4-bit floating point format, to optimize memory and speed. Benchmarks show it leads in accuracy and cost efficiency, offering up to 30% savings over other models. This positions Nemotron 3 Ultra as a top choice for developers needing robust AI capabilities.
Read originalThe 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.
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.