Models & Labs
NVIDIA Vera CPU Challenges Intel and AMD
NVIDIA Bloghigh confidence
Why it matters
- →Vera CPU offers significant performance improvements for AI workloads.
- →It challenges the dominance of traditional x86 CPUs from Intel and AMD.
- →Vera's efficiency and memory performance set new standards for AI infrastructure.
NVIDIA has unveiled its Vera CPU, which is set to challenge the dominance of Intel and AMD in the CPU market. The Vera CPU, equipped with 88 custom Olympus cores, delivers exceptional performance for AI-centric workloads, boasting a memory bandwidth of 1.2TB/s. Initial benchmarks by Phoronix reveal that Vera outperforms traditional x86 CPUs in both power efficiency and memory performance. This marks a significant generational leap from NVIDIA's previous Grace CPU. With its upcoming availability through partners, Vera is poised to become a key player in AI infrastructure.
Read originalMore from NVIDIA Blog
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.