Releases

Release notes for Dynamo v1.0.0 and newer are mirrored here from the GitHub releases, with breaking changes tracked on the Deprecations ledger and known issues on the Known Issues page. Patch releases are folded into their base release’s page. Earlier releases link to GitHub.

For the artifact inventory each release shipped — container images, wheels, Helm charts, crates — see Release Artifacts.

Agents and automation: Releases (machine-readable) renders this release data as generated markdown tables, with JSON and Atom twins in-repo at docs/fern/assets/releases.json and docs/fern/assets/releases-atom.xml.

v1.3.0GA releaseGitHub ↗Jul 20, 2026

Tool-calling and reasoning overhaul, RL rollout serving, the largest Router buildout to date, SLA-driven Planner autoscaling, and production GPU Memory Service on Kubernetes.

v1.3.0-dev.1Early accessJun 9, 2026

Full-platform preview of v1.3.0: complete runtime matrix, wheels on pypi.nvidia.com, crates, and Helm charts. Superseded by v1.3.0 GA.

v1.2.1PatchGitHub ↗Jun 13, 2026

Patch release. Same backend pins as v1.2.0.

v1.2.0GA releaseGitHub ↗Jun 2, 2026

DGD/DGDR v1beta1, CRTC as the default KV router, inter-pod GPU Memory Service, Dynamo Snapshot on CRI-O/OpenShift, and DeepSeek-V4 recipes on vLLM.

v1.2.0-deepseek-v4-dev.3Model buildMay 9, 2026

DeepSeek-V4 Blackwell preview; vLLM + SGLang containers only.

v1.2.0-deepseek-v4-dev.2Model buildMay 1, 2026

DeepSeek-V4 Blackwell preview; vLLM + SGLang containers only.

v1.1.1PatchGitHub ↗May 5, 2026

Patch release. Same backend pins as v1.1.0.

v1.1.0GA releaseGitHub ↗May 1, 2026

Resilient KV routing at scale, Anthropic Messages API support, performance modeling and offline replay, and the multimodal embedding cache.

v1.1.0-dev.3Early accessApr 18, 2026

Partial platform preview: TRT-LLM runtime image + wheels only.

v1.1.0-dev.2Early accessApr 9, 2026

Partial platform preview: SGLang + TRT-LLM runtime images + wheels.

v1.1.0-dev.1Early accessMar 17, 2026

Platform preview: runtime matrix, wheels on pypi.nvidia.com, Helm charts.

v1.0.2PatchGitHub ↗Apr 22, 2026

No artifact additions or removals versus v1.0.0.

v1.0.1PatchGitHub ↗Mar 16, 2026

No artifact additions or removals versus v1.0.0.

v1.0.0GA releaseGitHub ↗Mar 12, 2026

First GA release: unified configuration, Kubernetes production readiness, multimodal serving, and the agents surface.

v0.9.1PatchMar 4, 2026

No artifact additions or removals versus v0.9.0.

v0.9.0GA releaseFeb 11, 2026

First publish of dynamo-tokens crate. Deprecated dynamo-graph Helm chart dropped from the publish stream.

v0.8.1.post3Patch

Post-train of v0.8.1: republished the TensorRT-LLM runtime image and PyPI wheels only, with TRT-LLM pinned to 1.2.0rc6.post3. Same CUDA support as v0.8.1.

v0.8.1.post2Patch

Post-train of v0.8.1: republished the TensorRT-LLM runtime image and PyPI wheels only, with TRT-LLM pinned to 1.2.0rc6.post2. Same CUDA support as v0.8.1.

v0.8.1.post1Patch

Post-train of v0.8.1: republished the TensorRT-LLM runtime image and PyPI wheels only, with TRT-LLM pinned to 1.2.0rc6.post1. Same CUDA support as v0.8.1.

v0.8.1PatchJan 23, 2026

Post trains .post1/.post2/.post3 republished the TRT-LLM runtime image and PyPI wheels only; each carried a distinct TRT-LLM pin (see the v0.8.1.post1/.post2/.post3 rows).

v0.8.0GA releaseJan 15, 2026

dynamo-frontend image and CUDA 13 variants for vLLM and SGLang. First publish of dynamo-memory and dynamo-config crates.

v0.7.1PatchDec 15, 2025

v0.7.0.post1Patch

Post-train of v0.7.0: TensorRT-LLM pin advanced to 1.2.0rc3 (v0.7.0 shipped 1.2.0rc2). Same CUDA support as v0.7.0.

v0.7.0GA releaseNov 26, 2025

v0.6.1.post1Patch

Post-train of v0.6.1: same backend pins as v0.6.1. Same CUDA support as v0.6.1.

v0.6.1PatchNov 6, 2025

v0.6.0GA releaseOct 28, 2025

Oldest release tracked on this page.