systems · nvidia

NVIDIA Dynamo

Datacentre-scale inference serving framework built around disaggregated serving: prefill and decode run on separate worker pools so each scales and schedules independently, with a KV-cache-aware router and a distributed KV store to move cache between them. Engine-agnostic — it sits above vLLM, TensorRT-LLM and SGLang rather than replacing them.

Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.
Re-check this yourself → Source → Full record →

What is recorded

Publishernvidia
OriginUnited States
LicenceApache-2.0
Pulls recorded here2

Elsewhere in the registry

All systems → Browse with filters → What will run on my hardware? →

Registry record as of 2026-08-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.