chore: update versions for 0.7.0 release (#4217)

Signed-off-by: Anant Sharma <anants@nvidia.com>

Cargo.lock

@@ -2140,7 +2140,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-async-openai"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "async-openai-macros",
  "backoff",
@@ -2178,14 +2178,14 @@ dependencies = [
 
 [[package]]
 name = "dynamo-config"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
 ]
 
 [[package]]
 name = "dynamo-engine-mistralrs"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "async-stream",
@@ -2203,7 +2203,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-llm"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "ahash",
  "aho-corasick",
@@ -2302,7 +2302,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-memory"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "cudarc 0.17.3",
@@ -2319,7 +2319,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-parsers"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "dynamo-async-openai",
@@ -2337,7 +2337,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-run"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "async-stream",
@@ -2365,7 +2365,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-runtime"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "arc-swap",
@@ -2432,7 +2432,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-tokens"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "bytemuck",
  "dashmap 6.1.0",
@@ -4333,7 +4333,7 @@ dependencies = [
 
 [[package]]
 name = "kvbm-py3"
-version = "0.1.0"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "async-stream",
@@ -4391,7 +4391,7 @@ checksum = "58f929b4d672ea937a23a1ab494143d968337a5f47e56d0815df1e0890ddf174"
 
 [[package]]
 name = "libdynamo_llm"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "async-once-cell",

Cargo.toml

@@ -33,7 +33,7 @@ default-members = [
 resolver = "3"
 
 [workspace.package]
-version = "0.6.1"
+version = "0.7.0"
 edition = "2024"
 description = "Dynamo Inference Framework"
 authors = ["NVIDIA Inc. <sw-dl-dynamo@nvidia.com>"]
@@ -44,15 +44,15 @@ keywords = ["llm", "genai", "inference", "nvidia", "distributed"]
 
 [workspace.dependencies]
 # Local crates
-dynamo-runtime = { path = "lib/runtime", version = "0.6.1" }
-dynamo-llm = { path = "lib/llm", version = "0.6.1" }
-dynamo-config = { path = "lib/config", version = "0.6.1" }
-dynamo-tokens = { path = "lib/tokens", version = "0.6.1" }
-dynamo-async-openai = { path = "lib/async-openai", version = "0.6.1", features = [
+dynamo-runtime = { path = "lib/runtime", version = "0.7.0" }
+dynamo-llm = { path = "lib/llm", version = "0.7.0" }
+dynamo-config = { path = "lib/config", version = "0.7.0" }
+dynamo-tokens = { path = "lib/tokens", version = "0.7.0" }
+dynamo-async-openai = { path = "lib/async-openai", version = "0.7.0", features = [
     "byot",
     "rustls",
 ] }
-dynamo-parsers = { path = "lib/parsers", version = "0.6.1" }
+dynamo-parsers = { path = "lib/parsers", version = "0.7.0" }
 
 # External dependencies
 anyhow = { version = "1" }

deploy/cloud/helm/crds/Chart.yaml

@@ -16,5 +16,5 @@ apiVersion: v2
 name: dynamo-crds
 description: A Helm chart for dynamo CRDs
 type: application
-version: 0.6.1
+version: 0.7.0
 dependencies: []
\ No newline at end of file

deploy/cloud/helm/platform/Chart.yaml

@@ -19,7 +19,7 @@ maintainers:
     url: https://www.nvidia.com
 description: A Helm chart for NVIDIA Dynamo Platform.
 type: application
-version: 0.6.1
+version: 0.7.0
 home: https://nvidia.com
 dependencies:
   - name: dynamo-operator

deploy/helm/chart/Chart.yaml

@@ -17,5 +17,5 @@ apiVersion: v2
 name: dynamo-graph
 description: A Helm chart to deploy a Dynamo graph on Kubernetes
 type: application
-version: 0.6.1
-appVersion: 0.6.1
+version: 0.7.0
+appVersion: 0.7.0
\ No newline at end of file

docs/reference/support-matrix.md

@@ -56,8 +56,8 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
 
 | **Python Package** | **Version** | glibc version                         | CUDA Version |
 | :----------------- | :---------- | :------------------------------------ | :----------- |
-| ai-dynamo          | 0.6.1       | >=2.28                                |              |
-| ai-dynamo-runtime  | 0.6.1       | >=2.28 (Python 3.12 has known issues) |              |
+| ai-dynamo          | 0.7.0       | >=2.28                                |              |
+| ai-dynamo-runtime  | 0.7.0       | >=2.28 (Python 3.12 has known issues) |              |
 | NIXL               | 0.7.0       | >=2.27                                | >=11.8       |
 
 ### Build Dependency

lib/bindings/python/Cargo.lock

@@ -1419,7 +1419,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-async-openai"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "async-openai-macros",
  "backoff",
@@ -1445,7 +1445,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-llm"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "ahash",
  "aho-corasick",
@@ -1529,7 +1529,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-parsers"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "dynamo-async-openai",
@@ -1547,7 +1547,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-py3"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "async-stream",
@@ -1584,7 +1584,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-runtime"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "arc-swap",

lib/bindings/python/Cargo.toml

@@ -7,7 +7,7 @@
 
 [package]
 name = "dynamo-py3"
-version = "0.6.1"
+version = "0.7.0"
 edition = "2024"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

lib/bindings/python/pyproject.toml

@@ -16,7 +16,7 @@
 
 [project]
 name = "ai-dynamo-runtime"
-version = "0.6.1"
+version = "0.7.0"
 description = "Dynamo Inference Framework Runtime"
 readme = "README.md"
 authors = [

lib/kvbm/Cargo.toml

@@ -4,7 +4,7 @@
 
 [package]
 name = "kvbm-py3"
-version = "0.1.0"
+version = "0.7.0"
 edition = "2024"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

lib/kvbm/pyproject.toml

@@ -16,7 +16,7 @@
 
 [project]
 name = "kvbm"
-version = "0.6.1"
+version = "0.7.0"
 description = "Dynamo KVBM"
 readme = "README.md"
 authors = [

lib/runtime/examples/Cargo.lock

@@ -657,7 +657,7 @@ dependencies = [
 
 [[package]]
 name = "dynamo-runtime"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "arc-swap",
@@ -1038,7 +1038,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
 [[package]]
 name = "hello_world"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "dynamo-runtime",
@@ -2632,7 +2632,7 @@ dependencies = [
 
 [[package]]
 name = "service_metrics"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "dynamo-runtime",
@@ -2809,7 +2809,7 @@ dependencies = [
 
 [[package]]
 name = "system_metrics"
-version = "0.6.1"
+version = "0.7.0"
 dependencies = [
  "anyhow",
  "dynamo-runtime",

lib/runtime/examples/Cargo.toml

@@ -10,7 +10,7 @@ members = [
 resolver = "3"
 
 [workspace.package]
-version = "0.6.1"
+version = "0.7.0"
 edition = "2024"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

pyproject.toml

@@ -3,7 +3,7 @@
 
 [project]
 name = "ai-dynamo"
-version = "0.6.1"
+version = "0.7.0"
 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==0.6.1",
+    "ai-dynamo-runtime==0.7.0",
     "pytest>=8.3.4",
     "types-psutil>=7.0.0.20250218",
     "kubernetes>=32.0.1,<33.0.0",