For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Digest
  • Getting Started
    • Quickstart
    • Introduction
    • Local Installation
    • Building from Source
    • Kubernetes Deployment
    • Contribution Guide
  • Resources
    • Support Matrix
    • Feature Matrix
    • Release Artifacts
    • Examples
    • Glossary
  • Digest
    • DynoSim: Simulating the Pareto Frontier
    • Dynamo Day 0 support for TokenSpeed
    • Multi-Turn Agentic Harnesses
    • Full-Stack Optimizations for Agentic Inference
    • Flash Indexer: Inter-Galactic KV Routing
  • Kubernetes Deployment
  • User Guides
    • Disaggregated Serving
    • KV Cache Aware Routing
    • KV Cache Offloading
    • Tool Calling
    • Reasoning
    • Agents
    • Multimodal
    • Diffusion
    • LoRA Adapters
    • Fastokens Tokenizer
    • Observability (Local)
    • Fault Tolerance
    • Benchmarking
    • Writing Python Workers
    • Writing Python Unified Backends
    • Writing Rust Unified Backends
  • Backends
    • SGLang
    • TensorRT-LLM
    • vLLM
  • Components
    • Frontend
    • Router
    • Planner
    • Profiler
    • KVBM
  • Integrations
    • LMCache
    • FlexKV
    • KV Events for Custom Engines
  • Design Docs
    • Overall Architecture
    • Architecture Flow
    • Disaggregated Serving
    • Distributed Runtime
  • Documentation
    • Dynamo Docs Guide
NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.

LogoLogoDocumentation
Digest
Digest

DynoSim: Simulating the Pareto Frontier

Yongming Ding, Rudy Pei, Hongkuan Zhou, Ryan Olson, Dan Gil, Alec Flowers and Vikram Sharma Mailthody — May 2026

||View as Markdown|

DynoSim Pareto frontier plot showing explored configurations and GPU-verified configurations.

DynoSim is a workload-driven discrete-event simulation of NVIDIA Dynamo: a Dynamo twin for exploring LLM serving behavior before running full deployments. It brings measured engine forward-pass timing, Mocker scheduler cores, Router and Planner behavior, KV cache effects, and workload traces onto one virtual timeline. In our blog post, DynoSim: Simulating the Pareto Frontier, we show how simulation becomes the inner loop for design exploration: sweep broadly, map the throughput-latency Pareto frontier, shortlist the most promising candidates, and verify them on real clusters.

Last updated May 29, 2026

Previous

Dynamo Digest

Next

Dynamo Day 0 support for TokenSpeed