Skip to content

GitLab

Unverified Commit aeb42f22 authored by dagil-nvidia's avatar dagil-nvidia Committed by GitHub
Browse files

docs: bump version references to v1.0.1 and add v1.1.0-dev.1 pre-release artifacts (#7469)

parent 7ff5e0be
Hide whitespace changes
Inline Side-by-side
Showing with 161 additions and 64 deletions
README.md
View file @ aeb42f22
...@@ -104,7 +104,7 @@ Most inference engines optimize a single GPU or a single node. Dynamo is the **o ...@@ -104,7 +104,7 @@ Most inference engines optimize a single GPU or a single node. Dynamo is the **o
```bash ```bash
# Pull a prebuilt container (SGLang example) # Pull a prebuilt container (SGLang example)
docker run --gpus all --network host --rm -it nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.0.0 docker run --gpus all --network host --rm -it nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.0.1
# Inside the container — start frontend and worker # Inside the container — start frontend and worker
python3 -m dynamo.frontend --http-port 8000 --discovery-backend file > /dev/null 2>&1 & python3 -m dynamo.frontend --http-port 8000 --discovery-backend file > /dev/null 2>&1 &
...@@ -118,7 +118,7 @@ curl -s localhost:8000/v1/chat/completions -H "Content-Type: application/json" - ...@@ -118,7 +118,7 @@ curl -s localhost:8000/v1/chat/completions -H "Content-Type: application/json" -
}' | jq }' | jq
``` ```
Also available: [`tensorrtllm-runtime:1.0.0`](https://docs.nvidia.com/dynamo/resources/release-artifacts) and [`vllm-runtime:1.0.0`](https://docs.nvidia.com/dynamo/resources/release-artifacts). Also available: [`tensorrtllm-runtime:1.0.1`](https://docs.nvidia.com/dynamo/resources/release-artifacts) and [`vllm-runtime:1.0.1`](https://docs.nvidia.com/dynamo/resources/release-artifacts).
### Option B: Install from PyPI ### Option B: Install from PyPI
......
docs/reference/feature-matrix.md
View file @ aeb42f22
...@@ -6,7 +6,7 @@ title: Feature Matrix ...@@ -6,7 +6,7 @@ title: Feature Matrix
This document provides a comprehensive compatibility matrix for key Dynamo features across the supported backends. This document provides a comprehensive compatibility matrix for key Dynamo features across the supported backends.
*Updated for Dynamo v1.0.0* *Updated for Dynamo v1.0.1*
**Legend:** **Legend:**
* ✅ : Supported * ✅ : Supported
......
docs/reference/release-artifacts.md
View file @ aeb42f22
...@@ -10,26 +10,28 @@ This document provides a comprehensive inventory of all Dynamo release artifacts ...@@ -10,26 +10,28 @@ This document provides a comprehensive inventory of all Dynamo release artifacts
Release history in this document begins at v0.6.0. Release history in this document begins at v0.6.0.
## Current Release: Dynamo v1.0.0 ## Current Release: Dynamo v1.0.1
- **GitHub Release:** [v1.0.0](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.0) - **GitHub Release:** [v1.0.1](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.1)
- **Docs:** [v1.0.0](https://docs.dynamo.nvidia.com/dynamo) - **Docs:** [v1.0.1](https://docs.dynamo.nvidia.com/dynamo)
- **NGC Collection:** [ai-dynamo](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/collections/ai-dynamo) - **NGC Collection:** [ai-dynamo](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/collections/ai-dynamo)
> **Experimental:** [v1.1.0-dev.1](#pre-release-artifacts) is available as an experimental preview. See [Pre-Release Artifacts](#pre-release-artifacts) for container images, wheels, and Helm charts.
### Container Images ### Container Images
| Image:Tag | Description | Backend | CUDA | Arch | NGC | Notes | | Image:Tag | Description | Backend | CUDA | Arch | NGC | Notes |
|-----------|-------------|---------|------|------|-----|-------| |-----------|-------------|---------|------|------|-----|-------|
| `vllm-runtime:1.0.0` | Runtime container for vLLM backend | vLLM `v0.16.0` | `v12.9` | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/vllm-runtime?version=1.0.0) | | | `vllm-runtime:1.0.1` | Runtime container for vLLM backend | vLLM `v0.16.0` | `v12.9` | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/vllm-runtime?version=1.0.1) | |
| `vllm-runtime:1.0.0-cuda13` | Runtime container for vLLM backend (CUDA 13) | vLLM `v0.16.0` | `v13.0` | AMD64/ARM64* | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/vllm-runtime?version=1.0.0-cuda13) | | | `vllm-runtime:1.0.1-cuda13` | Runtime container for vLLM backend (CUDA 13) | vLLM `v0.16.0` | `v13.0` | AMD64/ARM64* | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/vllm-runtime?version=1.0.1-cuda13) | |
| `vllm-runtime:1.0.0-efa-amd64` | Runtime container for vLLM with AWS EFA | vLLM `v0.16.0` | `v12.9` | AMD64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/vllm-runtime?version=1.0.0-efa-amd64) | Experimental | | `vllm-runtime:1.0.1-efa-amd64` | Runtime container for vLLM with AWS EFA | vLLM `v0.16.0` | `v12.9` | AMD64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/vllm-runtime?version=1.0.1-efa-amd64) | Experimental |
| `sglang-runtime:1.0.0` | Runtime container for SGLang backend | SGLang `v0.5.9` | `v12.9` | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/sglang-runtime?version=1.0.0) | | | `sglang-runtime:1.0.1` | Runtime container for SGLang backend | SGLang `v0.5.9` | `v12.9` | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/sglang-runtime?version=1.0.1) | |
| `sglang-runtime:1.0.0-cuda13` | Runtime container for SGLang backend (CUDA 13) | SGLang `v0.5.9` | `v13.0` | AMD64/ARM64* | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/sglang-runtime?version=1.0.0-cuda13) | | | `sglang-runtime:1.0.1-cuda13` | Runtime container for SGLang backend (CUDA 13) | SGLang `v0.5.9` | `v13.0` | AMD64/ARM64* | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/sglang-runtime?version=1.0.1-cuda13) | |
| `tensorrtllm-runtime:1.0.0` | Runtime container for TensorRT-LLM backend | TRT-LLM `v1.3.0rc5.post1` | `v13.1` | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/tensorrtllm-runtime?version=1.0.0) | | | `tensorrtllm-runtime:1.0.1` | Runtime container for TensorRT-LLM backend | TRT-LLM `v1.3.0rc5.post1` | `v13.1` | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/tensorrtllm-runtime?version=1.0.1) | |
| `tensorrtllm-runtime:1.0.0-efa-amd64` | Runtime container for TensorRT-LLM with AWS EFA | TRT-LLM `v1.3.0rc5.post1` | `v13.1` | AMD64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/tensorrtllm-runtime?version=1.0.0-efa-amd64) | Experimental | | `tensorrtllm-runtime:1.0.1-efa-amd64` | Runtime container for TensorRT-LLM with AWS EFA | TRT-LLM `v1.3.0rc5.post1` | `v13.1` | AMD64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/tensorrtllm-runtime?version=1.0.1-efa-amd64) | Experimental |
| `dynamo-frontend:1.0.0` | API gateway with Endpoint Prediction Protocol (EPP) | — | — | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/dynamo-frontend?version=1.0.0) | | | `dynamo-frontend:1.0.1` | API gateway with Endpoint Prediction Protocol (EPP) | — | — | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/dynamo-frontend?version=1.0.1) | |
| `kubernetes-operator:1.0.0` | Kubernetes operator for Dynamo deployments | — | — | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/kubernetes-operator?version=1.0.0) | | | `kubernetes-operator:1.0.1` | Kubernetes operator for Dynamo deployments | — | — | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/kubernetes-operator?version=1.0.1) | |
| `snapshot-agent:1.0.0` | Snapshot agent for fast GPU worker recovery via CRIU | — | — | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/snapshot-agent?version=1.0.0) | Preview | | `snapshot-agent:1.0.1` | Snapshot agent for fast GPU worker recovery via CRIU | — | — | AMD64/ARM64 | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/containers/snapshot-agent?version=1.0.1) | Preview |
\* Multimodal inference on CUDA 13 images: works on AMD64 for all backends; works on ARM64 only for TensorRT-LLM (`vllm-runtime:*-cuda13` and `sglang-runtime:*-cuda13` do not support multimodality on ARM64). \* Multimodal inference on CUDA 13 images: works on AMD64 for all backends; works on ARM64 only for TensorRT-LLM (`vllm-runtime:*-cuda13` and `sglang-runtime:*-cuda13` do not support multimodality on ARM64).
...@@ -39,16 +41,16 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl ...@@ -39,16 +41,16 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl
| Package | Description | Python | Platform | PyPI | | Package | Description | Python | Platform | PyPI |
|---------|-------------|--------|----------|------| |---------|-------------|--------|----------|------|
| `ai-dynamo==1.0.0` | Main package with backend integrations (vLLM, SGLang, TRT-LLM) | `3.10`–`3.12` | Linux (glibc `v2.28+`) | [link](https://pypi.org/project/ai-dynamo/1.0.0/) | | `ai-dynamo==1.0.1` | Main package with backend integrations (vLLM, SGLang, TRT-LLM) | `3.10`–`3.12` | Linux (glibc `v2.28+`) | [link](https://pypi.org/project/ai-dynamo/1.0.1/) |
| `ai-dynamo-runtime==1.0.0` | Core Python bindings for Dynamo runtime | `3.10`–`3.12` | Linux (glibc `v2.28+`) | [link](https://pypi.org/project/ai-dynamo-runtime/1.0.0/) | | `ai-dynamo-runtime==1.0.1` | Core Python bindings for Dynamo runtime | `3.10`–`3.12` | Linux (glibc `v2.28+`) | [link](https://pypi.org/project/ai-dynamo-runtime/1.0.1/) |
| `kvbm==1.0.0` | KV Block Manager for disaggregated KV cache | `3.12` | Linux (glibc `v2.28+`) | [link](https://pypi.org/project/kvbm/1.0.0/) | | `kvbm==1.0.1` | KV Block Manager for disaggregated KV cache | `3.12` | Linux (glibc `v2.28+`) | [link](https://pypi.org/project/kvbm/1.0.1/) |
### Helm Charts ### Helm Charts
| Chart | Description | NGC | | Chart | Description | NGC |
|-------|-------------|-----| |-------|-------------|-----|
| `dynamo-platform-1.0.0` | Platform services (etcd, NATS) and Dynamo Operator for Dynamo cluster | [link](https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform-1.0.0.tgz) | | `dynamo-platform-1.0.1` | Platform services (etcd, NATS) and Dynamo Operator for Dynamo cluster | [link](https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform-1.0.1.tgz) |
| `snapshot-1.0.0` | Snapshot DaemonSet for fast GPU worker recovery | [link](https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot-1.0.0.tgz) | | `snapshot-1.0.1` | Snapshot DaemonSet for fast GPU worker recovery | [link](https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot-1.0.1.tgz) |
> [!NOTE] > [!NOTE]
> The `dynamo-crds` Helm chart is deprecated as of v1.0.0; CRDs are now managed by the Dynamo Operator. The `dynamo-graph` Helm chart is deprecated as of v0.9.0. > The `dynamo-crds` Helm chart is deprecated as of v1.0.0; CRDs are now managed by the Dynamo Operator. The `dynamo-graph` Helm chart is deprecated as of v0.9.0.
...@@ -57,15 +59,15 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl ...@@ -57,15 +59,15 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl
| Crate | Description | MSRV (Rust) | crates.io | | Crate | Description | MSRV (Rust) | crates.io |
|-------|-------------|-------------|-----------| |-------|-------------|-------------|-----------|
| `dynamo-runtime@1.0.0` | Core distributed runtime library | `v1.82` | [link](https://crates.io/crates/dynamo-runtime/1.0.0) | | `dynamo-runtime@1.0.1` | Core distributed runtime library | `v1.82` | [link](https://crates.io/crates/dynamo-runtime/1.0.1) |
| `dynamo-llm@1.0.0` | LLM inference engine | `v1.82` | [link](https://crates.io/crates/dynamo-llm/1.0.0) | | `dynamo-llm@1.0.1` | LLM inference engine | `v1.82` | [link](https://crates.io/crates/dynamo-llm/1.0.1) |
| `dynamo-async-openai@1.0.0` | Async OpenAI-compatible API client | `v1.82` | [link](https://crates.io/crates/dynamo-async-openai/1.0.0) | | `dynamo-async-openai@1.0.1` | Async OpenAI-compatible API client | `v1.82` | [link](https://crates.io/crates/dynamo-async-openai/1.0.1) |
| `dynamo-parsers@1.0.0` | Protocol parsers (SSE, JSON streaming) | `v1.82` | [link](https://crates.io/crates/dynamo-parsers/1.0.0) | | `dynamo-parsers@1.0.1` | Protocol parsers (SSE, JSON streaming) | `v1.82` | [link](https://crates.io/crates/dynamo-parsers/1.0.1) |
| `dynamo-memory@1.0.0` | Memory management utilities | `v1.82` | [link](https://crates.io/crates/dynamo-memory/1.0.0) | | `dynamo-memory@1.0.1` | Memory management utilities | `v1.82` | [link](https://crates.io/crates/dynamo-memory/1.0.1) |
| `dynamo-config@1.0.0` | Configuration management | `v1.82` | [link](https://crates.io/crates/dynamo-config/1.0.0) | | `dynamo-config@1.0.1` | Configuration management | `v1.82` | [link](https://crates.io/crates/dynamo-config/1.0.1) |
| `dynamo-tokens@1.0.0` | Tokenizer bindings for LLM inference | `v1.82` | [link](https://crates.io/crates/dynamo-tokens/1.0.0) | | `dynamo-tokens@1.0.1` | Tokenizer bindings for LLM inference | `v1.82` | [link](https://crates.io/crates/dynamo-tokens/1.0.1) |
| `dynamo-mocker@1.0.0` | Inference engine simulator for benchmarking | `v1.82` | [link](https://crates.io/crates/dynamo-mocker/1.0.0) | | `dynamo-mocker@1.0.1` | Inference engine simulator for benchmarking | `v1.82` | [link](https://crates.io/crates/dynamo-mocker/1.0.1) |
| `dynamo-kv-router@1.0.0` | KV-aware request routing library | `v1.82` | [link](https://crates.io/crates/dynamo-kv-router/1.0.0) | | `dynamo-kv-router@1.0.1` | KV-aware request routing library | `v1.82` | [link](https://crates.io/crates/dynamo-kv-router/1.0.1) |
## Quick Install Commands ## Quick Install Commands
...@@ -76,22 +78,22 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl ...@@ -76,22 +78,22 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl
```bash ```bash
# Runtime containers # Runtime containers
docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0 docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.1
docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.0.0 docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.0.1
docker pull nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.0.0 docker pull nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.0.1
# CUDA 13 variants # CUDA 13 variants
docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0-cuda13 docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.1-cuda13
docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.0.0-cuda13 docker pull nvcr.io/nvidia/ai-dynamo/sglang-runtime:1.0.1-cuda13
# EFA variants (AWS, AMD64 only, experimental) # EFA variants (AWS, AMD64 only, experimental)
docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0-efa-amd64 docker pull nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.1-efa-amd64
docker pull nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.0.0-efa-amd64 docker pull nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.0.1-efa-amd64
# Infrastructure containers # Infrastructure containers
docker pull nvcr.io/nvidia/ai-dynamo/dynamo-frontend:1.0.0 docker pull nvcr.io/nvidia/ai-dynamo/dynamo-frontend:1.0.1
docker pull nvcr.io/nvidia/ai-dynamo/kubernetes-operator:1.0.0 docker pull nvcr.io/nvidia/ai-dynamo/kubernetes-operator:1.0.1
docker pull nvcr.io/nvidia/ai-dynamo/snapshot-agent:1.0.0 docker pull nvcr.io/nvidia/ai-dynamo/snapshot-agent:1.0.1
``` ```
### Python Wheels (PyPI) ### Python Wheels (PyPI)
...@@ -101,16 +103,16 @@ docker pull nvcr.io/nvidia/ai-dynamo/snapshot-agent:1.0.0 ...@@ -101,16 +103,16 @@ docker pull nvcr.io/nvidia/ai-dynamo/snapshot-agent:1.0.0
```bash ```bash
# Install Dynamo with a specific backend (Recommended) # Install Dynamo with a specific backend (Recommended)
uv pip install "ai-dynamo[vllm]==1.0.0" uv pip install "ai-dynamo[vllm]==1.0.1"
uv pip install "ai-dynamo[sglang]==1.0.0" uv pip install "ai-dynamo[sglang]==1.0.1"
# TensorRT-LLM requires the NVIDIA PyPI index and pip # TensorRT-LLM requires the NVIDIA PyPI index and pip
pip install --pre --extra-index-url https://pypi.nvidia.com "ai-dynamo[trtllm]==1.0.0" pip install --pre --extra-index-url https://pypi.nvidia.com "ai-dynamo[trtllm]==1.0.1"
# Install Dynamo core only # Install Dynamo core only
uv pip install ai-dynamo==1.0.0 uv pip install ai-dynamo==1.0.1
# Install standalone KVBM (Python 3.12 only) # Install standalone KVBM (Python 3.12 only)
uv pip install kvbm==1.0.0 uv pip install kvbm==1.0.1
``` ```
### Helm Charts (NGC) ### Helm Charts (NGC)
...@@ -119,8 +121,8 @@ uv pip install kvbm==1.0.0 ...@@ -119,8 +121,8 @@ uv pip install kvbm==1.0.0
> For Kubernetes deployment instructions, see the [Kubernetes Installation Guide](../kubernetes/installation-guide.md). > For Kubernetes deployment instructions, see the [Kubernetes Installation Guide](../kubernetes/installation-guide.md).
```bash ```bash
helm install dynamo-platform oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform --version 1.0.0 helm install dynamo-platform oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform --version 1.0.1
helm install snapshot oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot --version 1.0.0 helm install snapshot oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot --version 1.0.1
``` ```
### Rust Crates (crates.io) ### Rust Crates (crates.io)
...@@ -129,15 +131,15 @@ helm install snapshot oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot ...@@ -129,15 +131,15 @@ helm install snapshot oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot
> For API documentation, see each crate on [docs.rs](https://docs.rs/). To build Dynamo from source, see [Building from Source](https://github.com/ai-dynamo/dynamo#building-from-source). > For API documentation, see each crate on [docs.rs](https://docs.rs/). To build Dynamo from source, see [Building from Source](https://github.com/ai-dynamo/dynamo#building-from-source).
```bash ```bash
cargo add dynamo-runtime@1.0.0 cargo add dynamo-runtime@1.0.1
cargo add dynamo-llm@1.0.0 cargo add dynamo-llm@1.0.1
cargo add dynamo-async-openai@1.0.0 cargo add dynamo-async-openai@1.0.1
cargo add dynamo-parsers@1.0.0 cargo add dynamo-parsers@1.0.1
cargo add dynamo-memory@1.0.0 cargo add dynamo-memory@1.0.1
cargo add dynamo-config@1.0.0 cargo add dynamo-config@1.0.1
cargo add dynamo-tokens@1.0.0 cargo add dynamo-tokens@1.0.1
cargo add dynamo-mocker@1.0.0 cargo add dynamo-mocker@1.0.1
cargo add dynamo-kv-router@1.0.0 cargo add dynamo-kv-router@1.0.1
``` ```
**CUDA and Driver Requirements:** For detailed CUDA toolkit versions and minimum driver requirements for each container image, see the [Support Matrix](support-matrix.md#cuda-and-driver-requirements). **CUDA and Driver Requirements:** For detailed CUDA toolkit versions and minimum driver requirements for each container image, see the [Support Matrix](support-matrix.md#cuda-and-driver-requirements).
...@@ -145,6 +147,7 @@ cargo add dynamo-kv-router@1.0.0 ...@@ -145,6 +147,7 @@ cargo add dynamo-kv-router@1.0.0
## Known Issues ## Known Issues
For a complete list of known issues, refer to the release notes for each version: For a complete list of known issues, refer to the release notes for each version:
- [v1.0.1 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.1)
- [v1.0.0 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.0) - [v1.0.0 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.0)
- [v0.9.0 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.0) - [v0.9.0 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.0)
- [v0.8.1 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.8.1) - [v0.8.1 Release Notes](https://github.com/ai-dynamo/dynamo/releases/tag/v0.8.1)
...@@ -162,6 +165,8 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -162,6 +165,8 @@ For a complete list of known issues, refer to the release notes for each version
## Release History ## Release History
- **v1.1.0-dev.1** *(experimental)*: Preview release. SGLang `v0.5.9`, TRT-LLM `v1.3.0rc5.post1`, vLLM `v0.17.1`, NIXL `v0.10.1`. Not recommended for production use.
- **v1.0.1**: Patch release. Same backend versions as v1.0.0: SGLang `v0.5.9`, TRT-LLM `v1.3.0rc5.post1`, vLLM `v0.16.0`, NIXL `v0.10.1`.
- **v1.0.0**: First major release. SGLang `v0.5.9`, TRT-LLM `v1.3.0rc5.post1` (CUDA 13.1), vLLM `v0.16.0`, NIXL `v0.10.1`. New `snapshot-agent` container and `snapshot` Helm chart (Preview). New EFA container variants for vLLM and TRT-LLM (Experimental, AMD64 only). New `dynamo-mocker` and `dynamo-kv-router` Rust crates. Deprecated `dynamo-crds` Helm chart (CRDs now managed by the Operator). `v1alpha1` CRDs deprecated. - **v1.0.0**: First major release. SGLang `v0.5.9`, TRT-LLM `v1.3.0rc5.post1` (CUDA 13.1), vLLM `v0.16.0`, NIXL `v0.10.1`. New `snapshot-agent` container and `snapshot` Helm chart (Preview). New EFA container variants for vLLM and TRT-LLM (Experimental, AMD64 only). New `dynamo-mocker` and `dynamo-kv-router` Rust crates. Deprecated `dynamo-crds` Helm chart (CRDs now managed by the Operator). `v1alpha1` CRDs deprecated.
- **v0.9.1**: Updated TRT-LLM to `v1.3.0rc3`. All other backend versions unchanged from v0.9.0. - **v0.9.1**: Updated TRT-LLM to `v1.3.0rc3`. All other backend versions unchanged from v0.9.0.
- **v0.9.0.post1**: Fixed `dynamo-platform` Helm chart operator image tag (Helm chart only, NGC) - **v0.9.0.post1**: Fixed `dynamo-platform` Helm chart operator image tag (Helm chart only, NGC)
...@@ -174,9 +179,11 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -174,9 +179,11 @@ For a complete list of known issues, refer to the release notes for each version
### GitHub Releases ### GitHub Releases
| Version | Release Date | GitHub | Docs | | Version | Release Date | GitHub | Docs | Notes |
|---------|--------------|--------|------| |---------|--------------|--------|------|-------|
| `v1.0.0` | Mar 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.0) | [Docs](https://docs.dynamo.nvidia.com/dynamo) | | `v1.1.0-dev.1` | Mar 17, 2026 | [Branch](https://github.com/ai-dynamo/dynamo/tree/release/1.1.0-dev.1) | — | Experimental |
| `v1.0.1` | Mar 16, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.1) | [Docs](https://docs.dynamo.nvidia.com/dynamo) | |
| `v1.0.0` | Mar 12, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.0) | [Docs](https://docs.dynamo.nvidia.com/dynamo) | |
| `v0.9.1` | Mar 4, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.1) | [Docs](https://docs.dynamo.nvidia.com/dynamo) | | `v0.9.1` | Mar 4, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.1) | [Docs](https://docs.dynamo.nvidia.com/dynamo) |
| `v0.9.0` | Feb 11, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.0) | [Docs](https://docs.dynamo.nvidia.com/dynamo/v-0-9-0/) | | `v0.9.0` | Feb 11, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v0.9.0) | [Docs](https://docs.dynamo.nvidia.com/dynamo/v-0-9-0/) |
| `v0.8.1` | Jan 23, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v0.8.1) | [Docs](https://docs.nvidia.com/dynamo/v-0-8-1/) | | `v0.8.1` | Jan 23, 2026 | [Release](https://github.com/ai-dynamo/dynamo/releases/tag/v0.8.1) | [Docs](https://docs.nvidia.com/dynamo/v-0-8-1/) |
...@@ -197,6 +204,9 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -197,6 +204,9 @@ For a complete list of known issues, refer to the release notes for each version
| Image:Tag | vLLM | Arch | CUDA | Notes | | Image:Tag | vLLM | Arch | CUDA | Notes |
|-----------|------|------|------|-------| |-----------|------|------|------|-------|
| `vllm-runtime:1.0.1` | `v0.16.0` | AMD64/ARM64 | `v12.9` | |
| `vllm-runtime:1.0.1-cuda13` | `v0.16.0` | AMD64/ARM64* | `v13.0` | |
| `vllm-runtime:1.0.1-efa-amd64` | `v0.16.0` | AMD64 | `v12.9` | Experimental |
| `vllm-runtime:1.0.0` | `v0.16.0` | AMD64/ARM64 | `v12.9` | | | `vllm-runtime:1.0.0` | `v0.16.0` | AMD64/ARM64 | `v12.9` | |
| `vllm-runtime:1.0.0-cuda13` | `v0.16.0` | AMD64/ARM64* | `v13.0` | | | `vllm-runtime:1.0.0-cuda13` | `v0.16.0` | AMD64/ARM64* | `v13.0` | |
| `vllm-runtime:1.0.0-efa-amd64` | `v0.16.0` | AMD64 | `v12.9` | Experimental | | `vllm-runtime:1.0.0-efa-amd64` | `v0.16.0` | AMD64 | `v12.9` | Experimental |
...@@ -219,6 +229,8 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -219,6 +229,8 @@ For a complete list of known issues, refer to the release notes for each version
| Image:Tag | SGLang | Arch | CUDA | Notes | | Image:Tag | SGLang | Arch | CUDA | Notes |
|-----------|--------|------|------|-------| |-----------|--------|------|------|-------|
| `sglang-runtime:1.0.1` | `v0.5.9` | AMD64/ARM64 | `v12.9` | |
| `sglang-runtime:1.0.1-cuda13` | `v0.5.9` | AMD64/ARM64* | `v13.0` | |
| `sglang-runtime:1.0.0` | `v0.5.9` | AMD64/ARM64 | `v12.9` | | | `sglang-runtime:1.0.0` | `v0.5.9` | AMD64/ARM64 | `v12.9` | |
| `sglang-runtime:1.0.0-cuda13` | `v0.5.9` | AMD64/ARM64* | `v13.0` | | | `sglang-runtime:1.0.0-cuda13` | `v0.5.9` | AMD64/ARM64* | `v13.0` | |
| `sglang-runtime:0.9.1` | `v0.5.8` | AMD64/ARM64 | `v12.9` | | | `sglang-runtime:0.9.1` | `v0.5.8` | AMD64/ARM64 | `v12.9` | |
...@@ -240,6 +252,8 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -240,6 +252,8 @@ For a complete list of known issues, refer to the release notes for each version
| Image:Tag | TRT-LLM | Arch | CUDA | Notes | | Image:Tag | TRT-LLM | Arch | CUDA | Notes |
|-----------|---------|------|------|-------| |-----------|---------|------|------|-------|
| `tensorrtllm-runtime:1.0.1` | `v1.3.0rc5.post1` | AMD64/ARM64 | `v13.1` | |
| `tensorrtllm-runtime:1.0.1-efa-amd64` | `v1.3.0rc5.post1` | AMD64 | `v13.1` | Experimental |
| `tensorrtllm-runtime:1.0.0` | `v1.3.0rc5.post1` | AMD64/ARM64 | `v13.1` | | | `tensorrtllm-runtime:1.0.0` | `v1.3.0rc5.post1` | AMD64/ARM64 | `v13.1` | |
| `tensorrtllm-runtime:1.0.0-efa-amd64` | `v1.3.0rc5.post1` | AMD64 | `v13.1` | Experimental | | `tensorrtllm-runtime:1.0.0-efa-amd64` | `v1.3.0rc5.post1` | AMD64 | `v13.1` | Experimental |
| `tensorrtllm-runtime:0.9.1` | `v1.3.0rc3` | AMD64/ARM64 | `v13.0` | | | `tensorrtllm-runtime:0.9.1` | `v1.3.0rc3` | AMD64/ARM64 | `v13.0` | |
...@@ -261,6 +275,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -261,6 +275,7 @@ For a complete list of known issues, refer to the release notes for each version
| Image:Tag | Arch | Notes | | Image:Tag | Arch | Notes |
|-----------|------|-------| |-----------|------|-------|
| `dynamo-frontend:1.0.1` | AMD64/ARM64 | |
| `dynamo-frontend:1.0.0` | AMD64/ARM64 | | | `dynamo-frontend:1.0.0` | AMD64/ARM64 | |
| `dynamo-frontend:0.9.1` | AMD64/ARM64 | | | `dynamo-frontend:0.9.1` | AMD64/ARM64 | |
| `dynamo-frontend:0.9.0` | AMD64/ARM64 | | | `dynamo-frontend:0.9.0` | AMD64/ARM64 | |
...@@ -271,6 +286,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -271,6 +286,7 @@ For a complete list of known issues, refer to the release notes for each version
| Image:Tag | Arch | Notes | | Image:Tag | Arch | Notes |
|-----------|------|-------| |-----------|------|-------|
| `kubernetes-operator:1.0.1` | AMD64/ARM64 | |
| `kubernetes-operator:1.0.0` | AMD64/ARM64 | | | `kubernetes-operator:1.0.0` | AMD64/ARM64 | |
| `kubernetes-operator:0.9.1` | AMD64/ARM64 | | | `kubernetes-operator:0.9.1` | AMD64/ARM64 | |
| `kubernetes-operator:0.9.0` | AMD64/ARM64 | | | `kubernetes-operator:0.9.0` | AMD64/ARM64 | |
...@@ -286,6 +302,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -286,6 +302,7 @@ For a complete list of known issues, refer to the release notes for each version
| Image:Tag | Arch | Notes | | Image:Tag | Arch | Notes |
|-----------|------|-------| |-----------|------|-------|
| `snapshot-agent:1.0.1` | AMD64/ARM64 | Preview |
| `snapshot-agent:1.0.0` | AMD64/ARM64 | Preview | | `snapshot-agent:1.0.0` | AMD64/ARM64 | Preview |
### Python Wheels ### Python Wheels
...@@ -298,6 +315,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -298,6 +315,7 @@ For a complete list of known issues, refer to the release notes for each version
| Package | Python | Platform | Notes | | Package | Python | Platform | Notes |
|---------|--------|----------|-------| |---------|--------|----------|-------|
| `ai-dynamo==1.0.1` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
| `ai-dynamo==1.0.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | | | `ai-dynamo==1.0.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
| `ai-dynamo==0.9.1` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | | | `ai-dynamo==0.9.1` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
| `ai-dynamo==0.9.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | | | `ai-dynamo==0.9.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
...@@ -314,6 +332,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -314,6 +332,7 @@ For a complete list of known issues, refer to the release notes for each version
| Package | Python | Platform | Notes | | Package | Python | Platform | Notes |
|---------|--------|----------|-------| |---------|--------|----------|-------|
| `ai-dynamo-runtime==1.0.1` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
| `ai-dynamo-runtime==1.0.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | | | `ai-dynamo-runtime==1.0.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
| `ai-dynamo-runtime==0.9.1` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | | | `ai-dynamo-runtime==0.9.1` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
| `ai-dynamo-runtime==0.9.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | | | `ai-dynamo-runtime==0.9.0` | `3.10`–`3.12` | Linux (glibc `v2.28+`) | |
...@@ -330,6 +349,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -330,6 +349,7 @@ For a complete list of known issues, refer to the release notes for each version
| Package | Python | Platform | Notes | | Package | Python | Platform | Notes |
|---------|--------|----------|-------| |---------|--------|----------|-------|
| `kvbm==1.0.1` | `3.12` | Linux (glibc `v2.28+`) | |
| `kvbm==1.0.0` | `3.12` | Linux (glibc `v2.28+`) | | | `kvbm==1.0.0` | `3.12` | Linux (glibc `v2.28+`) | |
| `kvbm==0.9.1` | `3.12` | Linux (glibc `v2.28+`) | | | `kvbm==0.9.1` | `3.12` | Linux (glibc `v2.28+`) | |
| `kvbm==0.9.0` | `3.12` | Linux (glibc `v2.28+`) | | | `kvbm==0.9.0` | `3.12` | Linux (glibc `v2.28+`) | |
...@@ -364,6 +384,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -364,6 +384,7 @@ For a complete list of known issues, refer to the release notes for each version
| Chart | Notes | | Chart | Notes |
|-------|-------| |-------|-------|
| `dynamo-platform-1.0.1` | |
| `dynamo-platform-1.0.0` | | | `dynamo-platform-1.0.0` | |
| `dynamo-platform-0.9.1` | | | `dynamo-platform-0.9.1` | |
| `dynamo-platform-0.9.0-post1` | Helm fix: operator image tag | | `dynamo-platform-0.9.0-post1` | Helm fix: operator image tag |
...@@ -379,6 +400,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -379,6 +400,7 @@ For a complete list of known issues, refer to the release notes for each version
| Chart | Notes | | Chart | Notes |
|-------|-------| |-------|-------|
| `snapshot-1.0.1` | Preview |
| `snapshot-1.0.0` | Preview | | `snapshot-1.0.0` | Preview |
#### dynamo-graph (Helm chart) -- Deprecated #### dynamo-graph (Helm chart) -- Deprecated
...@@ -405,6 +427,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -405,6 +427,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-runtime@1.0.1` | `v1.82` | |
| `dynamo-runtime@1.0.0` | `v1.82` | | | `dynamo-runtime@1.0.0` | `v1.82` | |
| `dynamo-runtime@0.9.1` | `v1.82` | | | `dynamo-runtime@0.9.1` | `v1.82` | |
| `dynamo-runtime@0.9.0` | `v1.82` | | | `dynamo-runtime@0.9.0` | `v1.82` | |
...@@ -419,6 +442,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -419,6 +442,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-llm@1.0.1` | `v1.82` | |
| `dynamo-llm@1.0.0` | `v1.82` | | | `dynamo-llm@1.0.0` | `v1.82` | |
| `dynamo-llm@0.9.1` | `v1.82` | | | `dynamo-llm@0.9.1` | `v1.82` | |
| `dynamo-llm@0.9.0` | `v1.82` | | | `dynamo-llm@0.9.0` | `v1.82` | |
...@@ -433,6 +457,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -433,6 +457,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-async-openai@1.0.1` | `v1.82` | |
| `dynamo-async-openai@1.0.0` | `v1.82` | | | `dynamo-async-openai@1.0.0` | `v1.82` | |
| `dynamo-async-openai@0.9.1` | `v1.82` | | | `dynamo-async-openai@0.9.1` | `v1.82` | |
| `dynamo-async-openai@0.9.0` | `v1.82` | | | `dynamo-async-openai@0.9.0` | `v1.82` | |
...@@ -447,6 +472,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -447,6 +472,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-parsers@1.0.1` | `v1.82` | |
| `dynamo-parsers@1.0.0` | `v1.82` | | | `dynamo-parsers@1.0.0` | `v1.82` | |
| `dynamo-parsers@0.9.1` | `v1.82` | | | `dynamo-parsers@0.9.1` | `v1.82` | |
| `dynamo-parsers@0.9.0` | `v1.82` | | | `dynamo-parsers@0.9.0` | `v1.82` | |
...@@ -461,6 +487,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -461,6 +487,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-memory@1.0.1` | `v1.82` | |
| `dynamo-memory@1.0.0` | `v1.82` | | | `dynamo-memory@1.0.0` | `v1.82` | |
| `dynamo-memory@0.9.1` | `v1.82` | | | `dynamo-memory@0.9.1` | `v1.82` | |
| `dynamo-memory@0.9.0` | `v1.82` | | | `dynamo-memory@0.9.0` | `v1.82` | |
...@@ -471,6 +498,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -471,6 +498,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-config@1.0.1` | `v1.82` | |
| `dynamo-config@1.0.0` | `v1.82` | | | `dynamo-config@1.0.0` | `v1.82` | |
| `dynamo-config@0.9.1` | `v1.82` | | | `dynamo-config@0.9.1` | `v1.82` | |
| `dynamo-config@0.9.0` | `v1.82` | | | `dynamo-config@0.9.0` | `v1.82` | |
...@@ -481,6 +509,7 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -481,6 +509,7 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-tokens@1.0.1` | `v1.82` | |
| `dynamo-tokens@1.0.0` | `v1.82` | | | `dynamo-tokens@1.0.0` | `v1.82` | |
| `dynamo-tokens@0.9.1` | `v1.82` | | | `dynamo-tokens@0.9.1` | `v1.82` | |
| `dynamo-tokens@0.9.0` | `v1.82` | Initial | | `dynamo-tokens@0.9.0` | `v1.82` | Initial |
...@@ -489,10 +518,61 @@ For a complete list of known issues, refer to the release notes for each version ...@@ -489,10 +518,61 @@ For a complete list of known issues, refer to the release notes for each version
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-mocker@1.0.1` | `v1.82` | |
| `dynamo-mocker@1.0.0` | `v1.82` | Initial | | `dynamo-mocker@1.0.0` | `v1.82` | Initial |
#### dynamo-kv-router (crate) #### dynamo-kv-router (crate)
| Crate | MSRV (Rust) | Notes | | Crate | MSRV (Rust) | Notes |
|-------|-------------|-------| |-------|-------------|-------|
| `dynamo-kv-router@1.0.1` | `v1.82` | |
| `dynamo-kv-router@1.0.0` | `v1.82` | Initial | | `dynamo-kv-router@1.0.0` | `v1.82` | Initial |
---
## Pre-Release Artifacts
> [!WARNING]
> **Pre-Release artifacts do not go through QA validation.** Pre-release versions are experimental previews intended for early testing and feedback. They may contain bugs, breaking changes, or incomplete features. Use stable releases for production workloads.
### v1.1.0-dev.1
- **Branch:** [release/1.1.0-dev.1](https://github.com/ai-dynamo/dynamo/tree/release/1.1.0-dev.1)
- **GitHub Tag:** [v1.1.0-dev.1](https://github.com/ai-dynamo/dynamo/releases/tag/v1.1.0-dev.1)
- **Backends:** SGLang `v0.5.9` | TensorRT-LLM `v1.3.0rc5.post1` | vLLM `v0.17.1` | NIXL `v0.10.1`
#### Container Images
| Image:Tag | Backend | CUDA | Arch |
|-----------|---------|------|------|
| `vllm-runtime:1.1.0-dev.1` | vLLM `v0.17.1` | `v12.9` | AMD64/ARM64 |
| `vllm-runtime:1.1.0-dev.1-cuda13` | vLLM `v0.17.1` | `v13.0` | AMD64/ARM64* |
| `vllm-runtime:1.1.0-dev.1-efa-amd64` | vLLM `v0.17.1` | `v12.9` | AMD64 |
| `sglang-runtime:1.1.0-dev.1` | SGLang `v0.5.9` | `v12.9` | AMD64/ARM64 |
| `sglang-runtime:1.1.0-dev.1-cuda13` | SGLang `v0.5.9` | `v13.0` | AMD64/ARM64* |
| `tensorrtllm-runtime:1.1.0-dev.1` | TRT-LLM `v1.3.0rc5.post1` | `v13.1` | AMD64/ARM64 |
| `tensorrtllm-runtime:1.1.0-dev.1-efa-amd64` | TRT-LLM `v1.3.0rc5.post1` | `v13.1` | AMD64 |
| `dynamo-frontend:1.1.0-dev.1` | — | — | AMD64/ARM64 |
| `kubernetes-operator:1.1.0-dev.1` | — | — | AMD64/ARM64 |
| `snapshot-agent:1.1.0-dev.1` | — | — | AMD64/ARM64 |
#### Python Wheels
Available from [pypi.nvidia.com](https://pypi.nvidia.com/) (pre-release index):
```bash
uv pip install --pre --extra-index-url https://pypi.nvidia.com/ ai-dynamo==1.1.0.dev1
uv pip install --pre --extra-index-url https://pypi.nvidia.com/ ai-dynamo-runtime==1.1.0.dev1
uv pip install --pre --extra-index-url https://pypi.nvidia.com/ kvbm==1.1.0.dev1
```
#### Helm Charts
| Chart | NGC |
|-------|-----|
| `dynamo-platform-1.1.0-dev.1` | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/helm-charts/dynamo-platform?version=1.1.0-dev.1) |
| `snapshot-1.1.0-dev.1` | [link](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/helm-charts/snapshot?version=1.1.0-dev.1) |
#### Rust Crates
Not shipped for pre-release versions.
docs/reference/support-matrix.md
View file @ aeb42f22
...@@ -9,7 +9,9 @@ subtitle: Hardware, software, and build compatibility for Dynamo ...@@ -9,7 +9,9 @@ subtitle: Hardware, software, and build compatibility for Dynamo
## At a Glance ## At a Glance
**Latest stable release:** [v1.0.0](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.0) -- SGLang `0.5.9` | TensorRT-LLM `1.3.0rc5.post1` | vLLM `0.16.0` | NIXL `0.10.1` **Latest stable release:** [v1.0.1](https://github.com/ai-dynamo/dynamo/releases/tag/v1.0.1) -- SGLang `0.5.9` | TensorRT-LLM `1.3.0rc5.post1` | vLLM `0.16.0` | NIXL `0.10.1`
**Experimental release:** [v1.1.0-dev.1](https://github.com/ai-dynamo/dynamo/tree/release/1.1.0-dev.1) -- SGLang `0.5.9` | TensorRT-LLM `1.3.0rc5.post1` | vLLM `0.17.1` | NIXL `0.10.1`
| Requirement | Supported | | Requirement | Supported |
| :--- | :--- | | :--- | :--- |
...@@ -28,6 +30,8 @@ The following table shows the backend framework versions included with each Dyna ...@@ -28,6 +30,8 @@ The following table shows the backend framework versions included with each Dyna
| **Dynamo** | **SGLang** | **TensorRT-LLM** | **vLLM** | **NIXL** | | **Dynamo** | **SGLang** | **TensorRT-LLM** | **vLLM** | **NIXL** |
| :--- | :--- | :--- | :--- | :--- | | :--- | :--- | :--- | :--- | :--- |
| **main (ToT)** | `0.5.9` | `1.3.0rc7` | `0.17.1` | `0.10.1` | | **main (ToT)** | `0.5.9` | `1.3.0rc7` | `0.17.1` | `0.10.1` |
| **v1.1.0-dev.1** *(experimental)* | `0.5.9` | `1.3.0rc5.post1` | `0.17.1` | `0.10.1` |
| **v1.0.1** | `0.5.9` | `1.3.0rc5.post1` | `0.16.0` | `0.10.1` |
| **v1.0.0** | `0.5.9` | `1.3.0rc5.post1` | `0.16.0` | `0.10.1` | | **v1.0.0** | `0.5.9` | `1.3.0rc5.post1` | `0.16.0` | `0.10.1` |
| **v0.9.1** | `0.5.8` | `1.3.0rc3` | `0.14.1` | `0.9.0` | | **v0.9.1** | `0.5.8` | `1.3.0rc3` | `0.14.1` | `0.9.0` |
| **v0.9.0** | `0.5.8` | `1.3.0rc1` | `0.14.1` | `0.9.0` | | **v0.9.0** | `0.5.8` | `1.3.0rc1` | `0.14.1` | `0.9.0` |
...@@ -59,6 +63,11 @@ Dynamo container images include CUDA toolkit libraries. The host machine must ha ...@@ -59,6 +63,11 @@ Dynamo container images include CUDA toolkit libraries. The host machine must ha
| Dynamo Version | Backend | CUDA Toolkit | Min Driver | Notes | | Dynamo Version | Backend | CUDA Toolkit | Min Driver | Notes |
| :--- | :--- | :--- | :--- | :--- | | :--- | :--- | :--- | :--- | :--- |
| **1.0.1** | **SGLang** | 12.9 | 575.xx+ | |
| | | 13.0 | 580.xx+ | |
| | **TensorRT-LLM** | 13.1 | 580.xx+ | |
| | **vLLM** | 12.9 | 575.xx+ | |
| | | 13.0 | 580.xx+ | |
| **1.0.0** | **SGLang** | 12.9 | 575.xx+ | | | **1.0.0** | **SGLang** | 12.9 | 575.xx+ | |
| | | 13.0 | 580.xx+ | | | | | 13.0 | 580.xx+ | |
| | **TensorRT-LLM** | 13.1 | 580.xx+ | | | | **TensorRT-LLM** | 13.1 | 580.xx+ | |
......
fern/components/profiler/profiler_guide.md
View file @ aeb42f22
...@@ -66,7 +66,7 @@ Each DGDR requires a container image for profiling and deployment: ...@@ -66,7 +66,7 @@ Each DGDR requires a container image for profiling and deployment:
```yaml ```yaml
spec: spec:
image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0" image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.1"
``` ```
#### Quick Start: Deploy with DGDR #### Quick Start: Deploy with DGDR
...@@ -83,7 +83,7 @@ metadata: ...@@ -83,7 +83,7 @@ metadata:
spec: spec:
model: "Qwen/Qwen3-0.6B" model: "Qwen/Qwen3-0.6B"
backend: vllm backend: vllm
image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0" image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.1"
workload: workload:
isl: 3000 isl: 3000
...@@ -229,7 +229,7 @@ metadata: ...@@ -229,7 +229,7 @@ metadata:
spec: spec:
model: "Qwen/Qwen3-0.6B" model: "Qwen/Qwen3-0.6B"
backend: vllm backend: vllm
image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0" image: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.1"
workload: { ... } workload: { ... }
sla: { ... } sla: { ... }
......
fern/docs.yml
View file @ aeb42f22
...@@ -47,7 +47,7 @@ redirects: ...@@ -47,7 +47,7 @@ redirects:
- source: "/dynamo/resources/examples" - source: "/dynamo/resources/examples"
destination: "/dynamo/dev/resources/examples" destination: "/dynamo/dev/resources/examples"
# Version-scoped getting-started → resources redirects # Version-scoped getting-started → resources redirects
# Only for versions where these pages moved (dev, v1.0.0, latest). # Only for versions where these pages moved (dev, v1.0.0, v1.0.1, latest).
# Older versions (v0.9.x and below) still have pages under getting-started. # Older versions (v0.9.x and below) still have pages under getting-started.
- source: "/dynamo/dev/getting-started/support-matrix" - source: "/dynamo/dev/getting-started/support-matrix"
destination: "/dynamo/dev/resources/support-matrix" destination: "/dynamo/dev/resources/support-matrix"
...@@ -57,6 +57,14 @@ redirects: ...@@ -57,6 +57,14 @@ redirects:
destination: "/dynamo/dev/resources/release-artifacts" destination: "/dynamo/dev/resources/release-artifacts"
- source: "/dynamo/dev/getting-started/examples" - source: "/dynamo/dev/getting-started/examples"
destination: "/dynamo/dev/resources/examples" destination: "/dynamo/dev/resources/examples"
- source: "/dynamo/v1.0.1/getting-started/support-matrix"
destination: "/dynamo/v1.0.1/resources/support-matrix"
- source: "/dynamo/v1.0.1/getting-started/feature-matrix"
destination: "/dynamo/v1.0.1/resources/feature-matrix"
- source: "/dynamo/v1.0.1/getting-started/release-artifacts"
destination: "/dynamo/v1.0.1/resources/release-artifacts"
- source: "/dynamo/v1.0.1/getting-started/examples"
destination: "/dynamo/v1.0.1/resources/examples"
- source: "/dynamo/v1.0.0/getting-started/support-matrix" - source: "/dynamo/v1.0.0/getting-started/support-matrix"
destination: "/dynamo/v1.0.0/resources/support-matrix" destination: "/dynamo/v1.0.0/resources/support-matrix"
- source: "/dynamo/v1.0.0/getting-started/feature-matrix" - source: "/dynamo/v1.0.0/getting-started/feature-matrix"
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment