Enhancing LLM Inference with CPU-GPU Memory Sharing
NVIDIA introduces a unified memory architecture to optimize large language model inference, addressing memory constraints and improving performance.
NVIDIA Introduces GPU Memory Swap to Optimize AI Model Deployment Costs
NVIDIA's GPU memory swap technology aims to reduce costs and improve performance for deploying large language models by optimizing GPU utilization and minimizing latency.
NVIDIA Unveils CUDA Toolkit 13.0 Enhancements for Jetson Thor
NVIDIA announces CUDA Toolkit 13.0 for Jetson Thor, featuring a unified Arm ecosystem, enhanced virtual memory, and improved GPU sharing, streamlining development for edge computing.
NVIDIA Unveils Blackwell Ultra GPU: A Leap in AI Factory Technology
NVIDIA introduces the Blackwell Ultra GPU, advancing AI capabilities with increased performance, memory, and efficiency, setting a new standard for AI factories.
GitHub to Deprecate GPU Machine Type in Codespaces by August 2025
GitHub announces the deprecation of GPU machine types in Codespaces by August 29, 2025, in line with Azure's NCv3-series VMs retirement. Developers are advised to prepare for this transition.
NVIDIA Enhances Vector Search with GPU-Accelerated cuVS for Real-Time Data Retrieval
NVIDIA's cuVS introduces GPU-accelerated vector search, optimizing indexing and retrieval for AI applications. The latest release enhances performance with new algorithms and integrations.
NVIDIA's CUTLASS 4.0: Advancing GPU Performance with New Python Interface
NVIDIA unveils CUTLASS 4.0, introducing a Python interface to enhance GPU performance for deep learning and high-performance computing, utilizing CUDA Tensors and Spatial Microkernels.
NVIDIA's CUTLASS 3.x Enhances GEMM Kernel Design with Modular Abstractions
NVIDIA's CUTLASS 3.x introduces a modular, hierarchical system for GEMM kernel design, improving code readability and extending support to newer architectures like Hopper and Blackwell.
NVIDIA Run:ai Enhances AI Model Orchestration on AWS
NVIDIA Run:ai on AWS Marketplace offers a streamlined approach to GPU infrastructure management for AI workloads, integrating with key AWS services to optimize performance.
NVIDIA Unveils NCCL 2.27: Enhancing AI Training and Inference Efficiency
NVIDIA launches NCCL 2.27 to improve AI workloads with faster GPU communication, lower latency, and enhanced resilience, addressing the demands of modern AI infrastructures.