chore: update versions for 0.3.2 release (#1793)

c4935b34 · Anant Sharma · GitHub · 533b8cee · c4935b34 · c4935b34
Unverified Commit c4935b34 authored Jul 07, 2025 by Anant Sharma Committed by GitHub Jul 07, 2025
9 changed files
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1674,7 +1674,7 @@ dependencies = [

 [[package]]
 name = "dynamo-engine-llamacpp"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "async-stream",
 "dynamo-llm",
@@ -1686,7 +1686,7 @@ dependencies = [

 [[package]]
 name = "dynamo-engine-mistralrs"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "async-openai",
@@ -1704,7 +1704,7 @@ dependencies = [

 [[package]]
 name = "dynamo-llm"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "akin",
 "aligned-vec",
@@ -1778,7 +1778,7 @@ dependencies = [

 [[package]]
 name = "dynamo-run"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "async-openai",
@@ -1806,7 +1806,7 @@ dependencies = [

 [[package]]
 name = "dynamo-runtime"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "assert_matches",
@@ -1855,7 +1855,7 @@ dependencies = [

 [[package]]
 name = "dynamo-tokens"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "bytemuck",
 "derive-getters",
@@ -2893,7 +2893,7 @@ dependencies = [

 [[package]]
 name = "http"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "clap",
 "dynamo-llm",
@@ -3538,7 +3538,7 @@ checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"

 [[package]]
 name = "libdynamo_llm"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "async-once-cell",
@@ -3650,7 +3650,7 @@ dependencies = [

 [[package]]
 name = "llmctl"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "clap",
@@ -3850,7 +3850,7 @@ dependencies = [

 [[package]]
 name = "metrics"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "axum 0.6.20",
 "clap",
@@ -5592,7 +5592,7 @@ dependencies = [

 [[package]]
 name = "router"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "clap",
 "dynamo-llm",

--- a/Cargo.toml
+++ b/Cargo.toml
@@ -28,7 +28,7 @@ members = [
 resolver = "3"

 [workspace.package]
-version = "0.3.1"
+version = "0.3.2"
 edition = "2021"
 description = "Dynamo Inference Framework"
 authors = ["NVIDIA Inc. <sw-dl-dynamo@nvidia.com>"]
@@ -39,9 +39,9 @@ keywords = ["llm", "genai", "inference", "nvidia", "distributed", "dynamo"]

 [workspace.dependencies]
 # Local crates
-dynamo-runtime = { path = "lib/runtime", version = "0.3.1" }
-dynamo-llm = { path = "lib/llm", version = "0.3.1" }
-dynamo-tokens = { path = "lib/tokens", version = "0.3.1" }
+dynamo-runtime = { path = "lib/runtime", version = "0.3.2" }
+dynamo-llm = { path = "lib/llm", version = "0.3.2" }
+dynamo-tokens = { path = "lib/tokens", version = "0.3.2" }

 # External dependencies
 anyhow = { version = "1" }

--- a/container/Dockerfile.vllm
+++ b/container/Dockerfile.vllm
@@ -163,7 +163,7 @@ RUN uv pip install /workspace/wheels/nixl/*.whl
 ARG VLLM_REF="0.8.4"
 ARG VLLM_PATCH="vllm_v${VLLM_REF}-dynamo-kv-disagg-patch.patch"
 ARG VLLM_PATCHED_PACKAGE_NAME="ai_dynamo_vllm"
-ARG VLLM_PATCHED_PACKAGE_VERSION="0.8.4.post3"
+ARG VLLM_PATCHED_PACKAGE_VERSION="0.8.4.post4"
 ARG VLLM_MAX_JOBS=4
 RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \
    --mount=type=cache,target=/root/.cache/uv \

--- a/docs/support_matrix.md
+++ b/docs/support_matrix.md
@@ -70,9 +70,9 @@ If you are using a **GPU**, the following GPU models and architectures are suppo

 | **Python Package** | **Version**   | glibc version                        | CUDA Version |
 | :----------------- | :------------ | :----------------------------------- | :----------- |
-| ai-dynamo          | 0.3.1         | >=2.28                               |              |
-| ai-dynamo-runtime  | 0.3.1         | >=2.28 (Python 3.12 has known issues)|              |
-| ai-dynamo-vllm     | 0.8.4.post3¹  | >=2.28 (recommended)                 |              |
+| ai-dynamo          | 0.3.2         | >=2.28                               |              |
+| ai-dynamo-runtime  | 0.3.2         | >=2.28 (Python 3.12 has known issues)|              |
+| ai-dynamo-vllm     | 0.8.4.post4¹  | >=2.28 (recommended)                 |              |
 | NIXL               | 0.3.1         | >=2.27                               | >=11.8       |

 ### Build Dependency
@@ -80,12 +80,12 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
 | **Build Dependency** | **Version**                                                                      |
 | :------------------- | :------------------------------------------------------------------------------- |
 | **Base Container**   | [25.03](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda-dl-base/tags) |
-| **ai-dynamo-vllm**   | 0.8.4.post3¹                                                                     |
-| **TensorRT-LLM**     | 0.21.0rc²                                                                        |
+| **ai-dynamo-vllm**   | 0.8.4.post4¹                                                                     |
+| **TensorRT-LLM**     | 1.0.0rc²                                                                        |
 | **NIXL**             | 0.3.1                                                                            |

 > [!Important]
-> ¹ ai-dynamo-vllm `v0.8.4.post3` is a customized patch of `v0.8.4` from vLLM.
+> ¹ ai-dynamo-vllm `v0.8.4.post4` is a customized patch of `v0.8.4` from vLLM.
 >
 > ² Specific versions of TensorRT-LLM supported by Dynamo are subject to change.


--- a/lib/bindings/python/Cargo.lock
+++ b/lib/bindings/python/Cargo.lock
@@ -1116,7 +1116,7 @@ dependencies = [

 [[package]]
 name = "dynamo-llm"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "akin",
 "anyhow",
@@ -1181,7 +1181,7 @@ dependencies = [

 [[package]]
 name = "dynamo-py3"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "async-openai",
@@ -1207,7 +1207,7 @@ dependencies = [

 [[package]]
 name = "dynamo-runtime"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "async-nats",

--- a/lib/bindings/python/Cargo.toml
+++ b/lib/bindings/python/Cargo.toml
@@ -19,7 +19,7 @@

 [package]
 name = "dynamo-py3"
-version = "0.3.1"
+version = "0.3.2"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

--- a/lib/runtime/examples/Cargo.lock
+++ b/lib/runtime/examples/Cargo.lock
@@ -623,7 +623,7 @@ dependencies = [

 [[package]]
 name = "dynamo-runtime"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "anyhow",
 "async-nats",
@@ -994,7 +994,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"

 [[package]]
 name = "hello_world"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "dynamo-runtime",
 ]
@@ -2306,7 +2306,7 @@ dependencies = [

 [[package]]
 name = "service_metrics"
-version = "0.3.1"
+version = "0.3.2"
 dependencies = [
 "dynamo-runtime",
 "futures",

--- a/lib/runtime/examples/Cargo.toml
+++ b/lib/runtime/examples/Cargo.toml
@@ -21,7 +21,7 @@ members = [
 resolver = "3"

 [workspace.package]
-version = "0.3.1"
+version = "0.3.2"
 edition = "2021"
 authors = ["NVIDIA"]
 license = "Apache-2.0"

--- a/pyproject.toml
+++ b/pyproject.toml
@@ -15,7 +15,7 @@

 [project]
 name = "ai-dynamo"
-version = "0.3.1"
+version = "0.3.2"
 description = "Distributed Inference Framework"
 readme = "README.md"
 authors = [
@@ -28,7 +28,7 @@ dependencies = [
    "pytest>=8.3.4",
    "types-psutil==7.0.0.20250218",
    "kubernetes==32.0.1",
-    "ai-dynamo-runtime==0.3.1",
+    "ai-dynamo-runtime==0.3.2",
    "fastapi==0.115.6",
    "distro",
    # filelock: required by planner