GPU
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.
RAPIDS Introduces GPU Polars Streaming and Unified GNN API Enhancements
NVIDIA's RAPIDS suite version 25.06 unveils new features including GPU Polars streaming, a unified GNN API, and zero-code ML speedups, enhancing Python data science capabilities.
Efficient AI Pipelines: NVIDIA's NeMo Retriever Extraction on a Single GPU
NVIDIA's NeMo Retriever offers a streamlined solution for multimodal document extraction using a single GPU, enhancing AI pipelines' efficiency and reducing operational costs.
NVIDIA Enhances Multi-GPU Communication with NCCL 2.26 Release
NVIDIA's NCCL 2.26 introduces performance enhancements, improved monitoring, and quality of service features, optimizing multi-GPU and multinode communications for AI and HPC applications.
Aethir and Bitfinex Host Insightful AMA on Decentralized GPU Infrastructure
Aethir and Bitfinex held an AMA session exploring decentralized GPU infrastructure, its impact on AI and gaming, and future plans involving the $ATH token.
Aethir's Decentralized Infrastructure Gains Spotlight in Bitfinex AMA
Aethir's decentralized infrastructure for GPU computing was discussed in a recent AMA hosted by Bitfinex and BitFreedomGus, highlighting its impact on AI and gaming sectors.
Enhancing Molecular Dynamics with NVIDIA's Multi-Process Service
NVIDIA's Multi-Process Service optimizes GPU usage in molecular dynamics simulations, boosting throughput by running concurrent processes on a single GPU.
Kaggle Competition Winner Reveals Stacking Strategy with cuML
Kaggle Grandmaster Chris Deotte shares insights on winning the April 2025 Kaggle competition using stacking with cuML, leveraging GPU acceleration for fast and efficient modeling.