chore: version update for 0.9.0 (#5661)

Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>

chore: version update for 0.9.0 (#5661)
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
66c36996 · Pavithra Vijayakrishnan · GitHub · 546f1bbc · 66c36996 · 66c36996
Unverified Commit 66c36996 authored Jan 26, 2026 by Pavithra Vijayakrishnan Committed by GitHub Jan 26, 2026
17 changed files
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2226,7 +2226,7 @@ checksum = "e1d926b4d407d372f141f93bb444696142c29d32962ccbd3531117cf3aa0bfa9"
 [[package]]
 name = "dynamo-async-openai"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "async-openai-macros",
 "backoff",
@@ -2265,14 +2265,14 @@ dependencies = [
 [[package]]
 name = "dynamo-config"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 ]
 [[package]]
 name = "dynamo-engine-mistralrs"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "async-stream",
@@ -2290,7 +2290,7 @@ dependencies = [
 [[package]]
 name = "dynamo-llm"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "ahash",
 "aho-corasick",
@@ -2401,7 +2401,7 @@ dependencies = [
 [[package]]
 name = "dynamo-memory"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "cudarc",
@@ -2418,7 +2418,7 @@ dependencies = [
 [[package]]
 name = "dynamo-parsers"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "dynamo-async-openai",
@@ -2437,7 +2437,7 @@ dependencies = [
 [[package]]
 name = "dynamo-run"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "async-stream",
@@ -2465,7 +2465,7 @@ dependencies = [
 [[package]]
 name = "dynamo-runtime"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "arc-swap",
@@ -2543,7 +2543,7 @@ dependencies = [
 [[package]]
 name = "dynamo-tokens"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "bs58",
 "bytemuck",
@@ -4702,7 +4702,7 @@ checksum = "2874a2af47a2325c2001a6e6fad9b16a53b802102b528163885171cf92b15976"
 [[package]]
 name = "libdynamo_llm"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "async-once-cell",

--- a/Cargo.toml
+++ b/Cargo.toml
@@ -32,7 +32,7 @@ default-members = [
 resolver = "3"
 [workspace.package]
-version = "0.8.0"
+version = "0.9.0"
 edition = "2024"
 description = "Dynamo Inference Framework"
 authors = ["NVIDIA Inc. <sw-dl-dynamo@nvidia.com>"]
@@ -43,15 +43,15 @@ keywords = ["llm", "genai", "inference", "nvidia", "distributed"]
 [workspace.dependencies]
 # Local crates
-dynamo-runtime = { path = "lib/runtime", version = "0.8.0" }
+dynamo-runtime = { path = "lib/runtime", version = "0.9.0" }
-dynamo-llm = { path = "lib/llm", version = "0.8.0" }
+dynamo-llm = { path = "lib/llm", version = "0.9.0" }
-dynamo-config = { path = "lib/config", version = "0.8.0" }
+dynamo-config = { path = "lib/config", version = "0.9.0" }
-dynamo-tokens = { path = "lib/tokens", version = "0.8.0" }
+dynamo-tokens = { path = "lib/tokens", version = "0.9.0" }
-dynamo-async-openai = { path = "lib/async-openai", version = "0.8.0", features = [
+dynamo-async-openai = { path = "lib/async-openai", version = "0.9.0", features = [
    "byot",
    "rustls",
 ] }
-dynamo-parsers = { path = "lib/parsers", version = "0.8.0" }
+dynamo-parsers = { path = "lib/parsers", version = "0.9.0" }
 # External dependencies
 anyhow = { version = "1" }

--- a/deploy/helm/charts/crds/Chart.yaml
+++ b/deploy/helm/charts/crds/Chart.yaml
@@ -16,5 +16,5 @@ apiVersion: v2
 name: dynamo-crds
 description: A Helm chart for dynamo CRDs
 type: application
-version: 0.8.0
+version: 0.9.0
 dependencies: []
\ No newline at end of file
--- a/deploy/helm/charts/platform/Chart.yaml
+++ b/deploy/helm/charts/platform/Chart.yaml
@@ -19,7 +19,7 @@ maintainers:
    url: https://www.nvidia.com
 description: A Helm chart for NVIDIA Dynamo Platform.
 type: application
-version: 0.8.0
+version: 0.9.0
 home: https://nvidia.com
 dependencies:
  - name: dynamo-operator

--- a/docs/reference/feature-matrix.md
+++ b/docs/reference/feature-matrix.md
@@ -2,7 +2,7 @@
 This document provides a comprehensive compatibility matrix for key Dynamo features across the supported backends.
-*Updated for Dynamo v0.8.0*
+*Updated for Dynamo v0.9.0*
 **Legend:**
 *   ✅ : Supported

--- a/lib/bindings/kvbm/Cargo.lock
+++ b/lib/bindings/kvbm/Cargo.lock
@@ -1557,7 +1557,7 @@ checksum = "e1d926b4d407d372f141f93bb444696142c29d32962ccbd3531117cf3aa0bfa9"
 [[package]]
 name = "dynamo-async-openai"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "async-openai-macros",
 "backoff",
@@ -1584,14 +1584,14 @@ dependencies = [
 [[package]]
 name = "dynamo-config"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 ]
 [[package]]
 name = "dynamo-llm"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "ahash",
 "aho-corasick",
@@ -1686,7 +1686,7 @@ dependencies = [
 [[package]]
 name = "dynamo-memory"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "cudarc 0.17.8",
@@ -1702,7 +1702,7 @@ dependencies = [
 [[package]]
 name = "dynamo-parsers"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "dynamo-async-openai",
@@ -1720,7 +1720,7 @@ dependencies = [
 [[package]]
 name = "dynamo-runtime"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "arc-swap",
@@ -3517,7 +3517,7 @@ dependencies = [
 [[package]]
 name = "kvbm-py3"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "async-stream",

--- a/lib/bindings/kvbm/Cargo.toml
+++ b/lib/bindings/kvbm/Cargo.toml
@@ -5,7 +5,7 @@
 [package]
 name = "kvbm-py3"
-version = "0.8.0"
+version = "0.9.0"
 edition = "2024"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

--- a/lib/bindings/kvbm/pyproject.toml
+++ b/lib/bindings/kvbm/pyproject.toml
@@ -16,7 +16,7 @@
 [project]
 name = "kvbm"
-version = "0.8.0"
+version = "0.9.0"
 description = "Dynamo KVBM"
 readme = "README.md"
 authors = [

--- a/lib/bindings/python/Cargo.lock
+++ b/lib/bindings/python/Cargo.lock
@@ -1566,7 +1566,7 @@ checksum = "e1d926b4d407d372f141f93bb444696142c29d32962ccbd3531117cf3aa0bfa9"
 [[package]]
 name = "dynamo-async-openai"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "async-openai-macros",
 "backoff",
@@ -1593,14 +1593,14 @@ dependencies = [
 [[package]]
 name = "dynamo-config"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 ]
 [[package]]
 name = "dynamo-llm"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "ahash",
 "aho-corasick",
@@ -1695,7 +1695,7 @@ dependencies = [
 [[package]]
 name = "dynamo-memory"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "cudarc",
@@ -1711,7 +1711,7 @@ dependencies = [
 [[package]]
 name = "dynamo-parsers"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "dynamo-async-openai",
@@ -1729,7 +1729,7 @@ dependencies = [
 [[package]]
 name = "dynamo-py3"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "async-stream",
@@ -1763,7 +1763,7 @@ dependencies = [
 [[package]]
 name = "dynamo-runtime"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "arc-swap",

--- a/lib/bindings/python/Cargo.toml
+++ b/lib/bindings/python/Cargo.toml
@@ -7,7 +7,7 @@
 [package]
 name = "dynamo-py3"
-version = "0.8.0"
+version = "0.9.0"
 edition = "2024"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

--- a/lib/bindings/python/pyproject.toml
+++ b/lib/bindings/python/pyproject.toml
@@ -16,7 +16,7 @@
 [project]
 name = "ai-dynamo-runtime"
-version = "0.8.0"
+version = "0.9.0"
 description = "Dynamo Inference Framework Runtime"
 readme = "README.md"
 authors = [

--- a/lib/gpu_memory_service/pyproject.toml
+++ b/lib/gpu_memory_service/pyproject.toml
@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "gpu-memory-service"
-version = "0.8.0"
+version = "0.9.0"
 description = "GPU Memory Service for Dynamo - CUDA VMM-based GPU memory allocation and sharing"
 readme = "README.md"
 authors = [

--- a/lib/gpu_memory_service/setup.py
+++ b/lib/gpu_memory_service/setup.py
@@ -46,7 +46,7 @@ def _create_ext_modules():
 setup(
    name="gpu-memory-service",
-    version="0.8.0",
+    version="0.9.0",
    description="GPU Memory Service for Dynamo - CUDA VMM-based GPU memory allocation and sharing",
    author="NVIDIA Inc.",
    author_email="sw-dl-dynamo@nvidia.com",

--- a/lib/runtime/examples/Cargo.lock
+++ b/lib/runtime/examples/Cargo.lock
@@ -873,14 +873,14 @@ checksum = "d0881ea181b1df73ff77ffaaf9c7544ecc11e82fba9b5f27b262a3c73a332555"
 [[package]]
 name = "dynamo-config"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 ]
 [[package]]
 name = "dynamo-runtime"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "arc-swap",
@@ -1364,7 +1364,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 [[package]]
 name = "hello_world"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "dynamo-runtime",
@@ -3463,7 +3463,7 @@ dependencies = [
 [[package]]
 name = "service_metrics"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "dynamo-runtime",
@@ -3650,7 +3650,7 @@ dependencies = [
 [[package]]
 name = "system_metrics"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
 "anyhow",
 "dynamo-runtime",

--- a/lib/runtime/examples/Cargo.toml
+++ b/lib/runtime/examples/Cargo.toml
@@ -10,7 +10,7 @@ members = [
 resolver = "3"
 [workspace.package]
-version = "0.8.0"
+version = "0.9.0"
 edition = "2024"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

--- a/pyproject.toml
+++ b/pyproject.toml
@@ -3,7 +3,7 @@
 [project]
 name = "ai-dynamo"
-version = "0.8.0"
+version = "0.9.0"
 description = "Distributed Inference Framework"
 readme = "README.md"
 authors = [
@@ -13,7 +13,7 @@ license = { text = "Apache-2.0" }
 license-files = ["LICENSE"]
 requires-python = ">=3.10"
 dependencies = [
-    "ai-dynamo-runtime==0.8.0",
+    "ai-dynamo-runtime==0.9.0",
    "transformers>=4.56.0",
    "pytest>=8.3.4",
    "types-psutil>=7.0.0.20250218",

--- a/recipes/README.md
+++ b/recipes/README.md
@@ -205,7 +205,7 @@ First, deploy the Dynamo Graph per instructions above.
 Then follow [Deploy Inference Gateway Section 2](../deploy/inference-gateway/README.md#2-deploy-inference-gateway) to install GAIE.
-Update the containers.epp.image in the deployment file, i.e. llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/deployment.yaml. It should match the release tag and be in the format `nvcr.io/nvidia/ai-dynamo/frontend:<version>` e.g. `nvcr.io/nvidia/ai-dynamo/frontend:0.8.0`
+Update the containers.epp.image in the deployment file, i.e. llama-3-70b/vllm/agg/gaie/k8s-manifests/epp/deployment.yaml. It should match the release tag and be in the format `nvcr.io/nvidia/ai-dynamo/frontend:<version>` e.g. `nvcr.io/nvidia/ai-dynamo/frontend:0.9.0`
 The recipe assumes you are using Kubernetes discovery backend and sets the `DYN_DISCOVERY_BACKEND` env variable in the epp deployment. If you want to use etcd enable the lines below and remove the DYN_DISCOVERY_BACKEND env var.
 ```bash
 - name: ETCD_ENDPOINTS