NVIDIA’s KAI Scheduler and vCluster Enable GPU Sharing in Kubernetes
NVIDIA introduces a solution for isolated Kubernetes clusters and efficient GPU sharing, reducing infrastructure costs for AI/ML teams.
Together AI Unveils Advanced Autoscaling for LLM Inference
Together AI introduces autoscaling features tailored for large language models, optimizing GPU use and managing latency during traffic spikes.
NVIDIA, Applied Materials Accelerate Semiconductor Innovation
NVIDIA and Applied Materials collaborate to advance semiconductor design with GPU-accelerated simulations and digital twins, addressing AI-driven demand.
NVIDIA CUDA Kernel Fusion Boosts GPU Efficiency in AI Workloads
NVIDIA's CUDA kernel fusion cuts memory traffic, kernel launch overhead, and speeds up AI and HPC tasks by up to 3x. Key for MoE and LLM training.
Nvidia NVSHMEM Boosts GROMACS GPU Scaling for Molecular Dynamics
Nvidia's NVSHMEM enables GPU-initiated communication, improving GROMACS scalability by eliminating CPU bottlenecks in molecular dynamics simulations.
NVIDIA (NVDA) Teams Up With AI Clouds to Scale Token Factories
NVIDIA partners with AI clouds to deploy large-scale AI factories, leveraging a new revenue-sharing model to meet soaring compute demand.
NVIDIA GQE Sets Benchmark for GPU-Accelerated Query Engines
NVIDIA's GPU Query Engine (GQE) leverages Grace Blackwell hardware to deliver 7.5x faster database performance compared to CPUs. Learn how.
NVIDIA Adds Vulkan Descriptor Heaps Support, Boosting GPU Performance
NVIDIA integrates VK_EXT_descriptor_heap in drivers and tools, enhancing Vulkan's resource binding efficiency for gaming and ray tracing.
AI Data Processing Shifts to GPUs: Key Trends and Impacts
AI pipelines are increasingly GPU-driven as inference-heavy workloads handle unstructured data, reshaping data processing and infrastructure demands.
NVIDIA Dynamo Snapshot Tackles Kubernetes AI Cold-Start Problem
NVIDIA's Dynamo Snapshot reduces Kubernetes AI inference cold-start times, leveraging CRIU and GPU Memory Service for sub-5-second deployment speed.