Models & Labs
HPE and NVIDIA Expand AI Factory for Agentic AI
NVIDIA Bloghigh confidence
Why it matters
- →The expansion supports the transition of agentic AI from concept to production.
- →NVIDIA Vera CPU and Agent Toolkit enhance real-time data processing and agent management.
- →NVIDIA Confidential Computing ensures secure handling of sensitive AI workloads.
Hewlett Packard Enterprise (HPE) and NVIDIA have expanded their AI Factory to support the development and deployment of agentic AI systems. This includes the introduction of the NVIDIA Vera CPU, designed for real-time data processing in agent systems, and the NVIDIA Agent Toolkit for managing autonomous agents. The expansion also features NVIDIA Confidential Computing for secure data handling. This collaboration aims to facilitate the transition of agentic AI from proof of concept to production, providing enterprises with the necessary tools and infrastructure for advanced AI applications.
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.