The NVIDIA DeepStream SDK is a comprehensive real-time streaming analytics toolkit based on GStreamer for AI-based multi-sensor processing, video, audio, and image understanding. It’s ideal for developers, software partners, startups, and OEMs building vision AI agents, applications, and services for a wide range of industries like smart cities, retail, manufacturing, and more.You can now create and deploy stream-processing pipelines that incorporate generative AI and other complex processing tasks like multi-camera tracking in minutes. To further accelerate development, DeepStream is also par
DeepStream SDK…a fully open, end-to-end data pipeline that spans pretraining, post-training, and interactive reinforcement learning—giving developers reproducible building blocks for agentic AI. Pretraining corpora : 10 trillion curated tokens, trained…
…These crypto and integrity accelerators are designed to be used as part of the KV pipeline, securing and validating KV flows without adding host CPU overhead. By leveraging standard NVMe and NVMe…
…Overcoming Pre- and Post-Processing Bottlenecks in AI Imaging and CV Pipelines with CV-CUDA Watch how Nsight Systems can be used to analyze performance markers and find optimization opportunities for cloud…
…She builds and optimizes enterprise-ready, multi-modal agentic AI systems and enables their large-scale deployment. Her experience includes advancing the optimization and adoption of GPU-accelerated inference pipelines and agent…
…and pipeline parallelism, allowing efficient closed-loop simulation, flexible integration of user-defined policies, and high-throughput evaluation of end-to-end AV models using NVIDIA's datasets and models. AI-generated…
…His current role focuses on advancing AI platforms and infrastructure to optimize machine learning pipelines, improve developer productivity, and support innovative AI solutions. His expertise includes managing geo-distributed teams and scaling…
…He builds production-grade systems for medical imaging and brings physical AI to healthcare—spanning GPU-accelerated pipelines, simulation, and cloud-edge deployment. He is also a core developer in open-source…
…geometric reasoning, and visual integrity—spanning seven Physical AI domains, including robotics, autonomous vehicles, and physics. These questions are generated by a VLM pipeline, refined by human experts, and released as open…
…The WAN-2.2 text-to-video submission used the TensorRT-LLM VisualGen , which accelerates diffusion-based video generation pipelines on NVIDIA GPUs. For DLRMv3, the submission was built on two open…
…Faster model support. “Hybrid” mode already provides Day 1 recommendations via speed-of-light estimates; we are also automating the silicon data-collection pipeline to accelerate fully validated support. Powering Dynamo deployments…