Ross ROSS = Recommend OSS · open-source software intelligence for agents

ai-dynamo/dynamo

A Datacenter Scale Distributed Inference Serving Framework observed · 2026-08-28

github.com/ai-dynamo/dynamo · homepage · Rust · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

87/100

  • Activity 99
  • Release rhythm 99
  • Longevity 39

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 14.5
  • age_days: 548
  • days_rel: 11
  • days_push: 7
  • n_releases_24m: 31

Full methodology

Adoption not part of the score

7872 stars · 1496 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

NVIDIA Dynamo is an open-source, datacenter-scale distributed inference serving framework that orchestrates inference engines like vLLM, SGLang, and TensorRT-LLM into coordinated multi-node systems. It provides disaggregated serving, KV-aware routing, multi-tier KV caching, and autoscaling, deployable on Kubernetes, Slurm, or locally.

Use cases

  • serve LLMs at datacenter scale across multiple nodes
  • run disaggregated prefill and decode serving for lower latency
  • route requests with KV-cache-aware routing to maximize cache reuse
  • offload and manage KV cache across memory tiers
  • autoscale inference workers on Kubernetes
  • deploy models with vLLM, SGLang, or TensorRT-LLM backends
  • serve multimodal and video generation workloads
  • benchmark inference performance with AIPerf

When to choose

  • you need multi-node, datacenter-scale LLM inference with high throughput
  • you want disaggregated prefill/decode serving with intelligent routing
  • you deploy inference on Kubernetes or Slurm with NVIDIA, AMD, or Intel accelerators
  • you want an orchestration layer on top of existing inference engines rather than replacing them

When to avoid

  • you just need to serve a single model on one GPU without distributed orchestration
  • you need a simple inference server with minimal operational complexity
  • your stack doesn't use supported engines like vLLM, SGLang, or TensorRT-LLM

Facets

framework · maturity active

llm-inference routing caching deployment microservices api-gateway monitoring benchmarking large-language-models artificial-intelligence gpu-computing microservices cloud-computing python rust cli self-hosted inference-serving disaggregated-serving kv-cache vllm sglang tensorrt-llm nvidia autoscaling kv-aware-routing prefill-decode-disaggregation containers devops kubernetes docker linux gpu

9 sources

Member repositories

RepositoryRoleHealth v2
ai-dynamo/dynamomain87

For agents

markdown · JSON · MCP: product_card(name="ai-dynamo/dynamo")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem