Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 4 additions & 4 deletions Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -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. <[email protected]>"]
Expand All @@ -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" }
Expand Down
2 changes: 1 addition & 1 deletion container/Dockerfile.vllm
Original file line number Diff line number Diff line change
Expand Up @@ -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 \
Expand Down
12 changes: 6 additions & 6 deletions docs/support_matrix.md
Original file line number Diff line number Diff line change
Expand Up @@ -70,22 +70,22 @@ 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

| **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.

Expand Down
6 changes: 3 additions & 3 deletions lib/bindings/python/Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion lib/bindings/python/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@

[package]
name = "dynamo-py3"
version = "0.3.1"
version = "0.3.2"
edition = "2021"
authors = ["NVIDIA"]
license = "Apache-2.0"
Expand Down
6 changes: 3 additions & 3 deletions lib/runtime/examples/Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion lib/runtime/examples/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -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"
Expand Down
4 changes: 2 additions & 2 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

[project]
name = "ai-dynamo"
version = "0.3.1"
version = "0.3.2"
description = "Distributed Inference Framework"
readme = "README.md"
authors = [
Expand All @@ -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
Expand Down
Loading