使用NVIDIA Dynamo的公司

The NVIDIA Dynamo Platform is a high-performance, low-latency inference platform designed to serve all AI models across any framework, architecture, or deployment scale. Whether you're running image recognition on a single entry-level GPU or deploying billion-parameter reasoning large language models (LLMs) across hundreds of thousands of data center GPUs, the NVIDIA Dynamo Platform delivers scalable, efficient AI inference. NVIDIA Dynamo is an open-source, low-latency, modular inference framework for serving generative AI models in distributed environments. It enables seamless scaling of inference workloads across large GPU fleets with intelligent resource scheduling and request routing, optimized memory management, and seamless data transfer. NVIDIA Dynamo supports all major AI inference backends and features large language model (LLM)-specific optimizations, such as disaggregated serving. When serving the open-source DeepSeek-R1 671B reasoning model on NVIDIA GB200 NVL72, NVIDIA Dynamo increased throughput—measured in tokens per second per GPU—by up to 30X. Serving the Llama 70B model on NVIDIA Hopper™, it increased throughput by more than 2X. NVIDIA Dynamo is the ideal solution for developers looking to accelerate and scale generative AI models with the highest efficiency at the lowest cost.