The Machine.
AI Factory Efficiency Lab
Model what your tokens and GPU capacity cost today, and what happens when efficiency or demand changes. Every figure is arithmetic on your own numbers.
Nothing you enter leaves your browser. The lab assumes no prices, throughput or benchmark figures. How it calculates
Technologies behind the numbers
Profiles of the NVIDIA software and systems this lab's questions touch, with what each one needs and when it is not needed.
- Framework
NVIDIA Dynamo
NVIDIA Dynamo is an open source framework that coordinates generative AI inference across many GPUs and nodes. It sits above engines such as vLLM, SGLang and TensorRT LLM and adds disaggregated serving, KV-cache-aware routing, cache offload and latency-driven autoscaling.
- Inference & runtime software
- Operations & orchestration
- Library
NVIDIA TensorRT LLM
NVIDIA TensorRT LLM (often written TensorRT-LLM) is an open source library that speeds up large language model and visual generation inference on NVIDIA GPUs, using custom kernels, quantization, in-flight batching, paged KV cache, speculative decoding and multi-GPU parallelism behind a Python LLM API.
- Inference & runtime software
- Microservice
NVIDIA NIM
NVIDIA NIM packages an AI model, an inference engine and its runtime into a container with standard APIs, so teams can self-host models on NVIDIA GPUs in the cloud, a data center, a workstation or at the edge instead of building their own serving stack.
- Inference & runtime software
- Operations & orchestration
- Platform
NVIDIA Run:ai
NVIDIA Run:ai is a Kubernetes-based platform that pools GPUs and schedules AI workloads across teams using quotas, priorities and fair sharing, so a shared cluster can serve notebooks, training and inference without each team owning fixed hardware.
- Operations & orchestration
- Platform
NVIDIA Mission Control
NVIDIA Mission Control is operations software for AI factories built on DGX and GB200/GB300 NVL72 systems. It brings cluster provisioning, Slurm and Kubernetes scheduling, health checks, automated recovery, power policies and building management integration into one supported control plane.
- Operations & orchestration
- Platform
NVIDIA DGX
NVIDIA DGX is NVIDIA's own line of AI systems, from the DGX Spark desktop to rack-scale DGX SuperPOD clusters, delivered together with NVIDIA operations software, reference architectures and support, so an organization can build AI infrastructure on one validated stack.
- Accelerated computing
- Operations & orchestration
Thank you. Your correction was sent.
The editors check it against the sources. If you left an email address, they may reply about it.