Models & Labs
NVIDIA Launches Vera CPU for Agentic AI
NVIDIA Bloghigh confidence
Why it matters
- →Vera is designed specifically for agentic AI, addressing unique computational needs.
- →It enhances AI infrastructure efficiency with custom cores and high memory bandwidth.
- →NVIDIA's launch positions it as a leader in the next phase of AI hardware development.
NVIDIA has introduced its first custom CPU, Vera, aimed at supporting agentic AI workloads. The Vera CPU, featuring 88 custom Olympus cores, is designed to handle the complex demands of AI agents, which extend beyond traditional GPU capabilities. Initial deliveries have been made to top AI labs including Anthropic, OpenAI, and SpaceXAI. This development marks a significant advancement in AI infrastructure, as Vera is built to enhance the efficiency and speed of AI operations. NVIDIA's move underscores its commitment to leading the next phase of AI computing with specialized hardware.
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.