NVIDIA In-Game Inferencing SDK
NVIDIA In-Game Inferencing SDK The NVIDIA In-Game Inferencing (NVIGI) SDK offers a streamlined and high performance path to integrate locally run AI models into games and applications via in-process…
Search
How to Build In-Vehicle AI Agents with NVIDIA: From Cloud to Car | NVIDIA Technical Blog
…Supporting LLMs, multimodal models, RAG, and agentic workflows, NeMo delivers scalable, production-ready AI applications. Integrated with NVIDIA accelerated computing and deployable via optimized microservices, it provides high performance, security, and portability…
Automate Kubernetes AI Cluster Health with NVSentinel | NVIDIA Technical Blog
…It integrates with NVIDIA Data Center GPU Manager (DCGM) and the NVIDIA GPU Operator to collect hardware health signals, classify issues by severity, and take automated actions such as quarantining or draining…
NVIDIA IGX Thor Powers Industrial, Medical, and Robotics Edge AI Applications | NVIDIA Technical Blog
…Designed for integration into custom carrier boards, the IGX T5000 SoM enables customers to build domain-specific industrial and robotic systems while accelerating time to production. NVIDIA IGX T7000 Board Kit : Scales…
Make Sense of Video Analytics by Integrating NVIDIA AI Blueprints | NVIDIA Technical Blog
Computer Vision / Video Analytics Make Sense of Video Analytics by Integrating NVIDIA AI Blueprints Nov 03, 2025 By Ilyas Bankole-Hameed , Jacob Liberman , Agerneh Dagnew and Shivam Lakhotia Discuss (0) Discuss (0…
Accelerating Long-Context Model Training in JAX and XLA | NVIDIA Technical Blog
…This composability is crucial for production training frameworks that rely on CUDA Graphs for performance optimization. Integrating NVSHMEM and XLA This section describes how NVSHMEM is integrated into the XLA compiler infrastructure…
How Centralized Radar Processing on NVIDIA DRIVE Enables Safer, Smarter Level 4 Autonomy | NVIDIA Technical Blog
…DRIVE AGX Thor using production ChengTech radar units. How centralized radar processing expands radar perception Most production automotive radars use edge processing architecture. Each sensor unit integrates its own system on chip…
NVIDIA Vera Rubin POD: Seven Chips, Five Rack-Scale Systems, One AI Supercomputer | NVIDIA Technical Blog
…accelerates time to first production. NVIDIA Vera Rubin DSX unifies chips, systems, software libraries, APIs, and a global partner ecosystem into a single architecture that tightly integrates compute, networking, storage, power, cooling…
NVIDIA Nsight Copilot
…Available via a Visual Studio Code extension and integration in the Nsight Compute kernel profiler. See Nsight Copilot in Action Combined with our specialized CUDA-aware LLM inference models, Nsight Copilot delivers…
How Justt Scaled Chargeback Extraction with Nemotron Parse
…a production-scale, enterprise deployment. System architecture To meet the performance, accuracy, and cost constraints, Justt designed a GPU-accelerated document processing architecture optimized for high-throughput inference. The system integrates Nemotron…