What does it do?
Dynamo is a datacenter-scale framework for serving AI inference across many GPUs or nodes. [1a][1b] It acts as an orchestration layer above inference engines, coordinating them into a multi-node inference system rather than replacing them. [2a][2b] A supported use case is serving large language models (LLMs) across multiple GPUs or nodes, including scaling the prefill and decode phases separately; prefill and decode are phases that can run in independently scalable GPU pools. [3a][3b]
Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
| Package | Version | Downloads · 30d | Trend · 30d |
|---|---|---|---|
dynamo-backend-commonv1.6.1 | v1.6.1 | — | — |
dynamo-benchv1.6.1 | v1.6.1 | — | — |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
dynamo-data-genv1.6.1 | v1.6.1 | — | — |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
dynamo-kv-hashingv1.6.1 | v1.6.1 | — | — |
dynamo-kv-routerv1.6.1 | v1.6.1 | — | — |
| — | — | — | |
| — | — | — | |
kvbm-commonv1.6.1 | v1.6.1 | — | — |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
| — | — | — | |
ai-dynamo-runtimev1.7.0.dev20261030 | v1.7.0.dev20261030 | ≥62.2K | |
| — | — | — | |
data-generatorv1.0.1 | v1.0.1 | ≥88 | |
| — | — | — | |
kvbmv1.6.1 | v1.6.1 | ≥2K |
README badges
Embed a badge in your README or website.
