Models & Labs
NVIDIA Vera CPU Powers New LANL Supercomputers
NVIDIA Bloghigh confidence
Why it matters
- →NVIDIA Vera CPUs significantly outperform traditional x86 CPUs, enhancing computational efficiency.
- →The integration of agentic AI in scientific research could transform hypothesis testing and experimentation.
- →The collaboration between LANL and NVIDIA exemplifies the potential of codesign in advancing scientific computing.
NVIDIA's Vera CPU is being integrated into new supercomputers at Los Alamos National Laboratory, aiming to enhance scientific discovery through advanced AI capabilities. The Mission and Vision systems will utilize the Vera CPU's superior performance, which surpasses traditional x86 CPUs by over three times, to support agentic AI in scientific research. These supercomputers, expected to be operational by 2027, will serve both classified national security and fundamental science research. This development continues a long-standing collaboration between LANL and NVIDIA, focusing on extreme codesign for simulation workloads.
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.