Models & Labs
NVIDIA Unveils AI Factories for Continuous Intelligence
NVIDIA Bloghigh confidence
Why it matters
- →AI factories represent a shift from traditional data centers to continuous intelligence production.
- →They optimize performance per watt, significantly reducing the cost of AI inference at scale.
- →This infrastructure enables enterprises to integrate AI more deeply into daily operations, enhancing productivity.
NVIDIA has introduced the concept of AI factories, a new class of infrastructure aimed at producing continuous intelligence. These factories convert energy into tokens, optimizing performance per watt to enhance efficiency and reduce costs. Utilizing advanced technologies like the NVIDIA Blackwell Ultra GPU and the Vera Rubin platform, AI factories promise up to 50x higher throughput per megawatt compared to previous generations. This development signifies a shift from traditional data centers to AI as a core infrastructure, enabling enterprises to scale AI capabilities more effectively.
Read originalMore from NVIDIA Blog
More 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.