Скачать или смотреть Introducing NVIDIA Dynamo: Low-Latency Distributed Inference for Scaling Reasoning LLMs

Learn how to deploy and scale reasoning LLMs using NVIDIA Dynamo, a new distributed inference serving framework designed for multi-node environments. Explore advanced serving techniques like disaggregated prefill and decode, and see how NVIDIA NIM enables fast, production-ready deployment of next-gen AI inference at scale.Learn how to deploy and scale reasoning LLMs using NVIDIA Dynamo, a new distributed inference serving framework designed for multi-node environments. Explore advanced serving techniques like disaggregated prefill and decode, and see how NVIDIA NIM enables fast, production-ready deployment of next-gen AI inference at scale.

Speakers:
Harry Kim, Principal Product Manager, NVIDIA
Neelay Shah, Principal Software Architect, NVIDIA
Ryan Olson, Distinguished Engineer / Solutions Architect, NVIDIA
Tanmay Verma, Senior System Software Engineer, NVIDIA

Replay of NVIDIA GTC Session ID S73042.

Level: Technical – Advanced
NVIDIA technology: TensorRT, DALI, NVLink / NVSwitch, and Triton

Login and join the free NVIDIA Developer Program to download the PDF: https://www.nvidia.com/en-us/on-deman...

Find more #GTC25 sessions via NVIDIA on demand: https://www.nvidia.com/en-us/on-deman...