> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt. # Releases (machine-readable) This page is a plain-markdown rendering of [`components/releases.data.ts`](https://github.com/ai-dynamo/dynamo/blob/main/docs/fern/components/releases.data.ts), the single source of truth behind [Compatibility](/dynamo/dev/reference/compatibility), [Release Artifacts](/dynamo/dev/reference/release-artifacts), [Model Early Access Builds](/dynamo/dev/reference/model-early-access-builds), and the [Release Notes](/dynamo/dev/reference/releases/release-history) timeline. It is regenerated by `scripts/gen_llms_tables.py` at every release bump — do not edit the tables below by hand. Append `.md` to this page's URL for a clean markdown export. The same data ships in-repo as JSON (`docs/fern/assets/releases.json`) and as an Atom feed (`docs/fern/assets/releases-atom.xml`). Current stable release: v1.3.0 (Jul 20, 2026; container tag `1.3.0`, wheel version `1.3.0.post1`). ## Releases | Version | Kind | Date | SGLang | TensorRT-LLM | vLLM | NIXL (SGL / TRT / vLLM) | UCX | Notes | Delta | | ------------------------ | ---------------- | ------------ | --------------------- | -------------- | ------ | ------------------------ | ------ | ------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | main (ToT) | development head | - | 0.5.15 | 1.3.0rc21 | 0.25.1 | 1.3.0 / 1.0.1 / 1.1.0 | - | - | - | | v1.3.0 | stable | Jul 20, 2026 | 0.5.14 | 1.3.0rc19 | 0.23.0 | 1.3.0 / 1.0.1 / 1.1.0 | 1.20.x | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-3-0) | CUDA 12 container images discontinued; EFA variants go multi-arch as -efa; GA wheels published as 1.3.0.post1 (containers stay :1.3.0); UCX 1.20.x. | | v1.3.0-dev.1 | platform-preview | Jun 9, 2026 | 0.5.12.post1 | 1.3.0rc17 | 0.22.0 | 1.0.1 / 0.10.1 / 1.1.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.3.0-dev.1) | 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 Superseded by v1.3.0 GA. | | v1.2.1 | patch | Jun 13, 2026 | 0.5.11 | 1.3.0rc14 | 0.20.1 | 1.0.1 / 0.10.1 / 0.10.1 | - | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-2-0) | Patch release. Same backend pins as v1.2.0. | | v1.2.0 | stable | Jun 2, 2026 | 0.5.11 | 1.3.0rc14 | 0.20.1 | 1.0.1 / 0.10.1 / 0.10.1 | 1.20.0 | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-2-0) | 603 PRs from 82 authors. DGD/DGDR promoted to v1beta1; CRTC default approximate KV router; inter-pod GMS sidecar; Dynamo Snapshot on CRI-O / OpenShift; UCX 1.20.0. | | v1.2.0-deepseek-v4-dev.3 | model-build | May 9, 2026 | upstream DSv4 preview | - | 0.20.1 | - / - / 0.10.1 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.2.0-deepseek-v4-dev.3) | DeepSeek-V4 Blackwell preview; vLLM + SGLang containers only. | | v1.2.0-deepseek-v4-dev.2 | model-build | May 1, 2026 | upstream DSv4 preview | - | 0.20.0 | - / - / 0.10.1 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.2.0-deepseek-v4-dev.2) | DeepSeek-V4 Blackwell preview; vLLM + SGLang containers only. | | v1.1.1 | patch | May 5, 2026 | 0.5.10.post1 | 1.3.0rc11 | 0.19.0 | 1.0.1 / 0.10.1 / 0.10.1 | - | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-1-0) | Patch release. Same backend pins as v1.1.0. | | v1.1.0 | stable | May 1, 2026 | 0.5.10.post1 | 1.3.0rc11 | 0.19.0 | 1.0.1 / 0.10.1 / 0.10.1 | 1.20 | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-1-0) | Planner split into its own dynamo-planner image (artifact boundary change). First 1.y.z publication of dynamo-protocols on crates.io; dynamo-async-openai deprecated at final 1.0.2. | | v1.1.0-dev.3 | platform-preview | Apr 18, 2026 | 0.5.10.post1 | 1.3.0rc11 | 0.19.0 | 1.0.1 / 0.10.1 / 0.10.1 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.1.0-dev.3) | Partial platform preview: TRT-LLM runtime image + wheels only. | | v1.1.0-dev.2 | platform-preview | Apr 9, 2026 | 0.5.9 | 1.3.0rc9 | 0.19.0 | 1.0.1 / 0.10.1 / 0.10.1 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.1.0-dev.2) | Partial platform preview: SGLang + TRT-LLM runtime images + wheels. | | v1.1.0-dev.1 | platform-preview | Mar 17, 2026 | 0.5.9 | 1.3.0rc5.post1 | 0.17.1 | 1.0.1 / 0.10.1 / 0.10.1 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.1.0-dev.1) | Platform preview: runtime matrix, wheels on pypi.nvidia.com, Helm charts. | | v1.0.2 | patch | Apr 22, 2026 | 0.5.9 | 1.3.0rc5.post1 | 0.16.0 | 0.10.1 / 0.10.1 / 0.10.1 | - | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-0-0) | No artifact additions or removals versus v1.0.0. | | v1.0.1 | patch | Mar 16, 2026 | 0.5.9 | 1.3.0rc5.post1 | 0.16.0 | 0.10.1 / 0.10.1 / 0.10.1 | - | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-0-0) | No artifact additions or removals versus v1.0.0. | | v1.0.0 | stable | Mar 12, 2026 | 0.5.9 | 1.3.0rc5.post1 | 0.16.0 | 0.10.1 / 0.10.1 / 0.10.1 | - | [release notes](https://docs.nvidia.com/dynamo/dev/reference/releases/v1-0-0) | snapshot-agent image and EFA variants for vLLM and TRT-LLM (AMD64 only). First publish of dynamo-mocker and dynamo-kv-router crates. snapshot Helm chart added (preview); deprecated dynamo-crds dropped from the publish stream. | | v0.9.1 | patch | Mar 4, 2026 | 0.5.8 | 1.3.0rc3 | 0.14.1 | 0.9.0 / 0.9.0 / 0.9.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.1) | No artifact additions or removals versus v0.9.0. | | v0.9.0 | stable | Feb 11, 2026 | 0.5.8 | 1.3.0rc1 | 0.14.1 | 0.9.0 / 0.9.0 / 0.9.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.0) | First publish of dynamo-tokens crate. Deprecated dynamo-graph Helm chart dropped from the publish stream. | | v0.8.1.post3 | patch | - | 0.5.6.post2 | 1.2.0rc6.post3 | 0.12.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | - | 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.post2 | patch | - | 0.5.6.post2 | 1.2.0rc6.post2 | 0.12.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | - | 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.post1 | patch | - | 0.5.6.post2 | 1.2.0rc6.post1 | 0.12.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | - | 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. | | v0.8.1 | patch | Jan 23, 2026 | 0.5.6.post2 | 1.2.0rc6.post1 | 0.12.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.8.1) | 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). | | v0.8.0 | stable | Jan 15, 2026 | 0.5.6.post2 | 1.2.0rc6.post1 | 0.12.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.8.0) | dynamo-frontend image and CUDA 13 variants for vLLM and SGLang. First publish of dynamo-memory and dynamo-config crates. | | v0.7.1 | patch | Dec 15, 2025 | 0.5.4.post3 | 1.2.0rc3 | 0.11.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.7.1) | - | | v0.7.0.post1 | patch | - | 0.5.4.post3 | 1.2.0rc3 | 0.11.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | - | 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. | | v0.7.0 | stable | Nov 26, 2025 | 0.5.4.post3 | 1.2.0rc2 | 0.11.0 | 0.8.0 / 0.8.0 / 0.8.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.7.0) | - | | v0.6.1.post1 | patch | - | 0.5.3.post2 | 1.1.0rc5 | 0.11.0 | 0.6.0 / 0.6.0 / 0.6.0 | - | - | Post-train of v0.6.1: same backend pins as v0.6.1. Same CUDA support as v0.6.1. | | v0.6.1 | patch | Nov 6, 2025 | 0.5.3.post2 | 1.1.0rc5 | 0.11.0 | 0.6.0 / 0.6.0 / 0.6.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.6.1) | - | | v0.6.0 | stable | Oct 28, 2025 | 0.5.3.post2 | 1.1.0rc5 | 0.11.0 | 0.6.0 / 0.6.0 / 0.6.0 | - | [release notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.6.0) | Oldest release tracked on this page. | Release highlights (stable releases): * v1.3.0: 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. * v1.2.0: 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. * v1.1.0: Resilient KV routing at scale, Anthropic Messages API support, performance modeling and offline replay, and the multimodal embedding cache. * v1.0.0: First GA release: unified configuration, Kubernetes production readiness, multimodal serving, and the agents surface. ## CUDA toolkit and minimum driver history | Dynamo | Backend | CUDA Toolkit | Min Driver | Note | | ------ | ------------ | ------------ | ---------- | ------------ | | 1.3.0 | SGLang | 13.0 | 580.xx+ | - | | 1.3.0 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.3.0 | vLLM | 13.0 | 580.xx+ | - | | 1.2.1 | SGLang | 12.9 | 575.xx+ | - | | 1.2.1 | SGLang | 13.0 | 580.xx+ | - | | 1.2.1 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.2.1 | vLLM | 12.9 | 575.xx+ | - | | 1.2.1 | vLLM | 13.0 | 580.xx+ | - | | 1.2.0 | SGLang | 12.9 | 575.xx+ | - | | 1.2.0 | SGLang | 13.0 | 580.xx+ | - | | 1.2.0 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.2.0 | vLLM | 12.9 | 575.xx+ | - | | 1.2.0 | vLLM | 13.0 | 580.xx+ | - | | 1.1.1 | SGLang | 12.9 | 575.xx+ | - | | 1.1.1 | SGLang | 13.0 | 580.xx+ | - | | 1.1.1 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.1.1 | vLLM | 12.9 | 575.xx+ | - | | 1.1.1 | vLLM | 13.0 | 580.xx+ | - | | 1.1.0 | SGLang | 12.9 | 575.xx+ | - | | 1.1.0 | SGLang | 13.0 | 580.xx+ | - | | 1.1.0 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.1.0 | vLLM | 12.9 | 575.xx+ | - | | 1.1.0 | vLLM | 13.0 | 580.xx+ | - | | 1.0.2 | SGLang | 12.9 | 575.xx+ | - | | 1.0.2 | SGLang | 13.0 | 580.xx+ | - | | 1.0.2 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.0.2 | vLLM | 12.9 | 575.xx+ | - | | 1.0.2 | vLLM | 13.0 | 580.xx+ | - | | 1.0.1 | SGLang | 12.9 | 575.xx+ | - | | 1.0.1 | SGLang | 13.0 | 580.xx+ | - | | 1.0.1 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.0.1 | vLLM | 12.9 | 575.xx+ | - | | 1.0.1 | vLLM | 13.0 | 580.xx+ | - | | 1.0.0 | SGLang | 12.9 | 575.xx+ | - | | 1.0.0 | SGLang | 13.0 | 580.xx+ | - | | 1.0.0 | TensorRT-LLM | 13.1 | 580.xx+ | - | | 1.0.0 | vLLM | 12.9 | 575.xx+ | - | | 1.0.0 | vLLM | 13.0 | 580.xx+ | - | | 0.9.1 | SGLang | 12.9 | 575.xx+ | - | | 0.9.1 | TensorRT-LLM | 13.0 | 580.xx+ | - | | 0.9.1 | vLLM | 12.9 | 575.xx+ | - | | 0.9.0 | SGLang | 12.9 | 575.xx+ | - | | 0.9.0 | TensorRT-LLM | 13.0 | 580.xx+ | - | | 0.9.0 | vLLM | 12.9 | 575.xx+ | - | | 0.8.1 | SGLang | 12.9 | 575.xx+ | - | | 0.8.1 | SGLang | 13.0 | 580.xx+ | Experimental | | 0.8.1 | TensorRT-LLM | 13.0 | 580.xx+ | - | | 0.8.1 | vLLM | 12.9 | 575.xx+ | - | | 0.8.1 | vLLM | 13.0 | 580.xx+ | Experimental | | 0.8.0 | SGLang | 12.9 | 575.xx+ | - | | 0.8.0 | SGLang | 13.0 | 580.xx+ | Experimental | | 0.8.0 | TensorRT-LLM | 13.0 | 580.xx+ | - | | 0.8.0 | vLLM | 12.9 | 575.xx+ | - | | 0.8.0 | vLLM | 13.0 | 580.xx+ | Experimental | | 0.7.1 | SGLang | 12.8 | 570.xx+ | - | | 0.7.1 | TensorRT-LLM | 13.0 | 580.xx+ | - | | 0.7.1 | vLLM | 12.9 | 575.xx+ | - | | 0.7.0 | SGLang | 12.9 | 575.xx+ | - | | 0.7.0 | TensorRT-LLM | 13.0 | 580.xx+ | - | | 0.7.0 | vLLM | 12.8 | 570.xx+ | - | * Patch versions (e.g. v0.8.1.post1, v0.7.0.post1) have the same CUDA support as their base version. * Early access v1.1.0-dev.\* images follow the same CUDA matrix as v1.0.2. The v1.2.0-deepseek-v4-dev.3 vLLM container is CUDA 13.0 multi-arch; the SGLang containers split by arch (CUDA 12.9 on amd64, CUDA 13.0 on arm64). * Experimental CUDA 13 images are not published for all versions. ## Feature support by backend (v1.3.0) | Feature | SGLang | TensorRT-LLM | vLLM | | --------------------- | ---------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------- | | Disaggregated Serving | Supported | Supported | Supported (Prefill/decode separation with NIXL KV transfer) | | KV-Aware Routing | Supported | Supported | Supported | | SLA-Based Planner | Supported | Supported | Supported | | KV Block Manager | Experimental (Work in progress across all combinations) | Supported | Supported | | Multimodal (Image) | Supported (Not compatible with KV-aware routing. Disagg patterns: EPD, E/PD, E/P/D (not traditional EP/D)) | Supported (Image URLs + pre-computed embeddings. Disagg: EP/D + E/P/D. KV-aware routing via dedicated MM Router Worker (requires KV event publishing)) | Supported (With KV-aware routing, image-aware routing on documented paths) | | Multimodal (Video) | Supported | Not supported | Supported (Video input with frame sampling) | | Multimodal (Audio) | Not supported | Not supported | Experimental (Qwen2-Audio, experimental) | | Request Migration | Supported | Supported (Work in progress with multimodal) | Supported | | Request Cancellation | Experimental (Remote-prefill-phase cancellation not supported in disaggregated mode) | Supported with caveat (Engine temporarily not notified of cancellations — resources for cancelled requests are not freed (known issue)) | Supported | | LoRA | Not supported | Not supported | Supported (Dynamic load/unload; KV-aware routing supports adapter affinity) | | Tool Calling | Supported | Supported | Supported | | Speculative Decoding | Experimental (Code hooks exist; no examples or docs yet) | Supported | Supported (Eagle3) | | Dynamo Snapshot | Supported | Not supported | Supported | ## Artifact inventory (v1.3.0) | Category | Name | Description | Meta | Tags / install | | --------- | -------------------------------- | --------------------------------------------------------------------------- | -------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | | container | vllm-runtime | vLLM backend runtime | vLLM v0.23.0 · CUDA 13.0 · AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.3.0`; `nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.3.0-efa` | | container | sglang-runtime | SGLang backend runtime | SGLang v0.5.14 · CUDA 13.0 · AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.3.0`; `nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.3.0-efa` | | container | tensorrtllm-runtime | TensorRT-LLM backend runtime | TRT-LLM v1.3.0rc19 · CUDA 13.1 · AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0`; `nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-efa` | | container | dynamo-frontend | OpenAI-compatible API gateway with Endpoint Prediction Protocol (EPP) | AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/dynamo-frontend:1.3.0` | | container | dynamo-planner | Standalone Planner used by Profiler jobs and Planner pods | AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/dynamo-planner:1.3.0` | | container | kubernetes-operator | Operator that manages Dynamo deployments and CRDs | AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/kubernetes-operator:1.3.0` | | container | snapshot-agent (Preview) | Fast GPU worker recovery via CRIU | AMD64/ARM64 | `nvcr.io/nvidia/ai-dynamo/snapshot-agent:1.3.0` | | wheel | ai-dynamo | Main package with backend integrations (vLLM, SGLang, TRT-LLM) | Python 3.10–3.12 · Linux (glibc v2.28+) | `uv pip install ai-dynamo==1.3.0.post1` | | wheel | ai-dynamo-runtime | Core Python bindings for the Dynamo runtime | Python 3.10–3.12 · Linux (glibc v2.28+) | `uv pip install ai-dynamo-runtime==1.3.0.post1` | | wheel | kvbm | KV Block Manager for disaggregated KV cache | Python 3.10–3.12 · Linux (glibc v2.28+) | `uv pip install kvbm==1.3.0.post1` | | helm | dynamo-platform | Platform services (etcd, NATS) and the Dynamo Operator for a Dynamo cluster | - | `helm install dynamo-platform oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform --version 1.3.0` | | helm | snapshot | Snapshot DaemonSet for fast GPU worker recovery | - | `helm install snapshot oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot --version 1.3.0` | | crate | dynamo-runtime | Core distributed runtime library | MSRV Rust v1.82 | `cargo add dynamo-runtime@1.3.0` | | crate | dynamo-llm | LLM inference engine | MSRV Rust v1.82 | `cargo add dynamo-llm@1.3.0` | | crate | dynamo-protocols | Async OpenAI-compatible API client | MSRV Rust v1.82 | `cargo add dynamo-protocols@1.3.0` | | crate | dynamo-async-openai (Deprecated) | Legacy OpenAI client; use dynamo-protocols | MSRV Rust v1.82 · final release | `cargo add dynamo-async-openai@1.0.2` | | crate | dynamo-parsers | Protocol parsers (SSE, JSON streaming) | MSRV Rust v1.82 | `cargo add dynamo-parsers@1.3.0` | | crate | dynamo-memory | Memory management utilities | MSRV Rust v1.82 | `cargo add dynamo-memory@1.3.0` | | crate | dynamo-config | Configuration management | MSRV Rust v1.82 | `cargo add dynamo-config@1.3.0` | | crate | dynamo-tokens | Tokenizer bindings for LLM inference | MSRV Rust v1.82 | `cargo add dynamo-tokens@1.3.0` | | crate | dynamo-tokenizers | Tokenizer library for LLM inference | MSRV Rust v1.82 | `cargo add dynamo-tokenizers@1.3.0` | | crate | dynamo-mocker | Inference engine simulator for benchmarking | MSRV Rust v1.82 | `cargo add dynamo-mocker@1.3.0` | | crate | dynamo-kv-router | KV-aware request routing library | MSRV Rust v1.82 | `cargo add dynamo-kv-router@1.3.0` | | crate | kvbm-logical | Logical layer for the KV Block Manager | MSRV Rust v1.82 | `cargo add kvbm-logical@1.3.0` | ## Known artifact issues | Release | Artifact | Issue | Status | | ------- | ------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------- | | v0.9.0 | dynamo-platform-0.9.0 | Helm chart sets operator image to 0.7.1 instead of 0.9.0. | Fixed in v0.9.0.post1 | | v0.8.1 | vllm-runtime:0.8.1-cuda13 | Container fails to launch. | Known issue | | v0.8.1 | sglang-runtime:0.8.1-cuda13, vllm-runtime:0.8.1-cuda13 | Multimodality not expected to work on ARM64. Works on AMD64. | Known limitation | | v0.8.0 | sglang-runtime:0.8.0-cuda13 | CuDNN installation issue caused PyTorch v2.9.1 compatibility problems with nn.Conv3d — performance degradation and excessive memory usage in multimodal workloads. | Fixed in v0.8.1 (#5461) | ## Crates: first published version on crates.io | Crate | First version | Date | | ------------------- | ------------- | ---------- | | dynamo-runtime | 0.1.0 | 2025-03-18 | | dynamo-llm | 0.2.0 | 2025-05-01 | | dynamo-async-openai | 0.4.1 | 2025-08-27 | | dynamo-parsers | 0.5.0 | 2025-09-18 | | dynamo-memory | 0.8.0 | 2026-01-15 | | dynamo-config | 0.8.0 | 2026-01-15 | | dynamo-tokens | 0.9.0 | 2026-02-12 | | dynamo-mocker | 1.0.0 | 2026-03-13 | | dynamo-kv-router | 1.0.0 | 2026-03-13 | | dynamo-protocols | 1.1.0 | 2026-05-04 | | dynamo-tokenizers | 1.2.0 | 2026-06-02 | ## Model early-access builds | Model | Tag | Release line | Runtimes | Shipped | GA path | Status | Coverage (images / wheels / helm / crates) | | ------------------- | -------------------------------- | ------------ | ------------------------------------------------- | ------------ | ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------ | | Inkling | `1.4.0-inkling-dev.1` | v1.4.0 | sglang-runtime | Jul 17, 2026 | Dev-only · v1.4.0 line | First build on the v1.4.0 line; targets the next stable release. | yes / no / no / no | | GLM-5.2 | `1.3.0-glm-5.2-dev.1` | v1.3.0 | sglang-runtime | Jul 20, 2026 | Dev-only | Container carries SGLang cherry-picks (stability, config parsing, model support) opened upstream but not yet in a released SGLang. | yes / no / no / no | | MiniMax-M3 | `1.3.0-minimax-m3-dev.1` | v1.3.0 | vllm-runtime, sglang-runtime, tensorrtllm-runtime | Jun 12, 2026 | Promoted → :1.3.0 | Dynamo changes and the M2 tool-calling fix are in release/1.3.0; the recipes run on the stock :1.3.0 containers. | yes / no / no / no | | DeepSeek-V4 | `1.3.0-deepseek-v4-dev.1` | v1.3.0 | tensorrtllm-runtime | Jun 6, 2026 | Recipe in v1.3.0 | DeepSeek-V4 Flash and Pro recipes ship in v1.3.0 on the standard TensorRT-LLM release container. | yes / no / no / no | | Nemotron-3-Ultra | `1.3.0-nemotron-ultra-dev.1` | v1.3.0 | vllm-runtime | Jun 5, 2026 | Dev-only | Four un-upstreamed vLLM patches; requires pinned flags VLLM\_DISABLED\_KERNELS=FlashInferFP8ScaledMMLinearKernel and --no-enable-flashinfer-autotune. | yes / no / no / no | | Nemotron-3-Super | `1.3.0-nemotron-super-dev.1` | v1.3.0 | vllm-runtime | Jun 4, 2026 | Promoted → :1.3.0 | Both container patches are in the vLLM v0.23.0 that v1.3.0 ships; the recipe runs on the stock vllm-runtime:1.3.0. | yes / no / no / no | | Kimi-K2.6 | `1.3.0-kimi-k2.6-dev.1` | v1.3.0 | vllm-runtime | Jun 4, 2026 | Promoted → :1.3.0 | The build's only container patch is in vLLM v0.23.0; the recipes run on the stock vllm-runtime:1.3.0. | yes / no / no / no | | Cosmos-3 | `1.3.0-cosmos3-dev.1` | v1.3.0 | vllm-runtime | Jun 1, 2026 | Dev-only | Dynamo #10132 (Cosmos3 support in the vLLM-Omni backend) is open, not merged — v1.3.0 containers cannot run Cosmos3. | yes / no / no / no | | DeepSeek-V4 preview | `1.2.0-deepseek-v4-dev.3` | v1.2.0 | vllm-runtime, sglang-runtime | May 9, 2026 | Superseded — recipe in v1.3.0 | Blackwell (B200 + GB200) preview; per-arch/CUDA tags (e.g. vllm-runtime:1.2.0-deepseek-v4-cuda13-dev.3). Superseded by the v1.3.0 recipe. | yes / no / no / no | | DeepSeek-V4 preview | `1.2.0-deepseek-v4-dev.2` | v1.2.0 | vllm-runtime, sglang-runtime | May 1, 2026 | Superseded — recipe in v1.3.0 | Blackwell preview on vLLM v0.20.0 (native DSv4 support); superseded by dev.3. | yes / no / no / no | | DeepSeek-V4 preview | `1.2.0-sglang-deepseek-v4-dev.1` | v1.2.0 | sglang-runtime | Apr 25, 2026 | Superseded — recipe in v1.3.0 | Earliest DSv4 preview (SGLang, B200 only); superseded by dev.2/dev.3. | yes / no / no / no | ## Platform-preview artifact coverage | Preview | Images | Wheels | Helm | Crates | | ------------ | ------ | ------ | ---- | ------ | | v1.3.0-dev.1 | yes | yes | yes | yes | | v1.1.0-dev.3 | yes | yes | no | no | | v1.1.0-dev.2 | yes | yes | no | no | | v1.1.0-dev.1 | yes | yes | yes | no | ## Platform support * GPU architectures: Blackwell, Hopper, Ada Lovelace, Ampere * OS: Ubuntu 24.04 (x86\_64, ARM64) — Supported * OS: Ubuntu 22.04 (x86\_64) — Supported * OS: CentOS Stream 9 (x86\_64) — Experimental * CSP: AWS — Amazon Linux 2023 (x86\_64) — Supported * CPU architectures: x86\_64, ARM64 (Ubuntu 24.04 only) * Wheels: Wheels are built in a manylinux\_2\_28-compatible environment and validated on CentOS Stream 9 and Ubuntu 22.04/24.04. Other Linux distributions are expected to work but are not officially verified. ## Release statistics | Release | PRs | Contributors | First-time contributors | Breaking changes | Known issues | | ------- | --- | ------------ | ----------------------- | ---------------- | ------------ | | v1.3.0 | 930 | 125 | 23 | 24 | 10 | | v1.2.0 | 603 | 82 | - | 5 | 11 | | v1.1.0 | 896 | 113 | 12 | 8 | 20 | | v1.0.0 | - | 90 | 34 | 41 | 14 | ## Nightlies ai-dynamo and ai-dynamo-runtime nightly builds from main publish wheels tagged \*.devYYYYMMDD (since Apr 24, 2026). Install with pip or uv using --pre and the NVIDIA extra-index pattern shown above.