Models & Labs
NVIDIA Blackwell Tops Agentic AI Benchmark
NVIDIA Bloghigh confidence
Why it matters
- →Agentic AI benchmarks provide a new way to measure AI system performance on complex tasks.
- →NVIDIA Blackwell's efficiency could significantly reduce costs for large-scale AI deployments.
- →This sets a new standard for evaluating AI infrastructure in real-world applications.
NVIDIA's Blackwell Ultra NVL72 platform has achieved top performance in the inaugural AgentPerf benchmark for agentic AI, developed by Artificial Analysis. This benchmark evaluates AI systems on their ability to handle complex, multi-step tasks, a departure from traditional AI benchmarks focused on single LLM calls. The Blackwell platform demonstrated the ability to run 20 times more agents per megawatt compared to NVIDIA Hopper, highlighting its efficiency in large-scale AI deployments. This performance is crucial for enterprises looking to optimize their AI infrastructure investments.
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.