Dynamo v1.6.2
Patch release refreshes runtime OS and Python packages, moves SGLang image to CPython 3.12.16, returns HTTP 400 on TensorRT-LLM token budget overrun, and adds opt-in GC freeze for SGLang workers.
The Deploy Log | Products | Free, no signup
Dynamo changelog
4 versions of Dynamo from NVIDIA in The Deploy Log. From to . On the median a new version every 13 days, publisher's dates only; the longest wait was 14 days. The newest is v1.6.2. 2 versions in the last 30 days. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| v1.6.2 | 14 | |
| v1.6.0 | 15 | |
| v1.5.1 | ||
| v1.5.0 |
Dynamo v1.6.0
Dynamo v1.6.0 released with pluggable flow control, TensorRT-LLM OpenEngine API sidecars, vLLM LoRA lifecycle, and separate engine/runtime containers.
Dynamo v1.5.1
Patch release fixes router overload recovery, min_tokens, Qwen3-VL video routing, and RL worker discovery.
Dynamo v1.5.0
Dynamo v1.5.0 adds custom Router scoring, Mooncake and disk KV indexing, and guided tool call streaming.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.