Unverified Commit e9cb035a authored by Harrison Saturley-Hall's avatar Harrison Saturley-Hall Committed by GitHub
Browse files

chore: bump versions and NIXL dependencies for 0.2.1 (#1012)

parent b2e401bc
...@@ -1521,7 +1521,7 @@ dependencies = [ ...@@ -1521,7 +1521,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-engine-llamacpp" name = "dynamo-engine-llamacpp"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"async-stream", "async-stream",
"dynamo-llm", "dynamo-llm",
...@@ -1533,7 +1533,7 @@ dependencies = [ ...@@ -1533,7 +1533,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-engine-mistralrs" name = "dynamo-engine-mistralrs"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-openai", "async-openai",
...@@ -1552,7 +1552,7 @@ dependencies = [ ...@@ -1552,7 +1552,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-engine-python" name = "dynamo-engine-python"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-openai", "async-openai",
...@@ -1573,7 +1573,7 @@ dependencies = [ ...@@ -1573,7 +1573,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-llm" name = "dynamo-llm"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"akin", "akin",
"anyhow", "anyhow",
...@@ -1636,7 +1636,7 @@ dependencies = [ ...@@ -1636,7 +1636,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-run" name = "dynamo-run"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-openai", "async-openai",
...@@ -1665,7 +1665,7 @@ dependencies = [ ...@@ -1665,7 +1665,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-runtime" name = "dynamo-runtime"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"assert_matches", "assert_matches",
...@@ -1714,7 +1714,7 @@ dependencies = [ ...@@ -1714,7 +1714,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-tokens" name = "dynamo-tokens"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"bytemuck", "bytemuck",
"derive-getters", "derive-getters",
...@@ -2709,7 +2709,7 @@ dependencies = [ ...@@ -2709,7 +2709,7 @@ dependencies = [
[[package]] [[package]]
name = "http" name = "http"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"clap", "clap",
"dynamo-llm", "dynamo-llm",
...@@ -3353,7 +3353,7 @@ checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa" ...@@ -3353,7 +3353,7 @@ checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
[[package]] [[package]]
name = "libdynamo_llm" name = "libdynamo_llm"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-once-cell", "async-once-cell",
...@@ -3466,7 +3466,7 @@ dependencies = [ ...@@ -3466,7 +3466,7 @@ dependencies = [
[[package]] [[package]]
name = "llmctl" name = "llmctl"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"clap", "clap",
"dynamo-llm", "dynamo-llm",
...@@ -3665,7 +3665,7 @@ dependencies = [ ...@@ -3665,7 +3665,7 @@ dependencies = [
[[package]] [[package]]
name = "metrics" name = "metrics"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"axum 0.6.20", "axum 0.6.20",
"clap", "clap",
...@@ -5356,7 +5356,7 @@ dependencies = [ ...@@ -5356,7 +5356,7 @@ dependencies = [
[[package]] [[package]]
name = "router" name = "router"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"clap", "clap",
"dynamo-llm", "dynamo-llm",
......
...@@ -28,7 +28,7 @@ members = [ ...@@ -28,7 +28,7 @@ members = [
resolver = "3" resolver = "3"
[workspace.package] [workspace.package]
version = "0.2.0" version = "0.2.1"
edition = "2021" edition = "2021"
description = "Dynamo Inference Framework" description = "Dynamo Inference Framework"
authors = ["NVIDIA Inc. <sw-dl-dynamo@nvidia.com>"] authors = ["NVIDIA Inc. <sw-dl-dynamo@nvidia.com>"]
...@@ -39,9 +39,9 @@ keywords = ["llm", "genai", "inference", "nvidia", "distributed", "dynamo"] ...@@ -39,9 +39,9 @@ keywords = ["llm", "genai", "inference", "nvidia", "distributed", "dynamo"]
[workspace.dependencies] [workspace.dependencies]
# Local crates # Local crates
dynamo-runtime = { path = "lib/runtime", version = "0.2.0" } dynamo-runtime = { path = "lib/runtime", version = "0.2.1" }
dynamo-llm = { path = "lib/llm", version = "0.2.0" } dynamo-llm = { path = "lib/llm", version = "0.2.1" }
dynamo-tokens = { path = "lib/tokens", version = "0.2.0" } dynamo-tokens = { path = "lib/tokens", version = "0.2.1" }
# External dependencies # External dependencies
anyhow = { version = "1" } anyhow = { version = "1" }
......
...@@ -146,7 +146,7 @@ RUN if [ "$ARCH" = "arm64" ]; then \ ...@@ -146,7 +146,7 @@ RUN if [ "$ARCH" = "arm64" ]; then \
ARG VLLM_REF="0.8.4" ARG VLLM_REF="0.8.4"
ARG VLLM_PATCH="vllm_v${VLLM_REF}-dynamo-kv-disagg-patch.patch" ARG VLLM_PATCH="vllm_v${VLLM_REF}-dynamo-kv-disagg-patch.patch"
ARG VLLM_PATCHED_PACKAGE_NAME="ai_dynamo_vllm" ARG VLLM_PATCHED_PACKAGE_NAME="ai_dynamo_vllm"
ARG VLLM_PATCHED_PACKAGE_VERSION="0.8.4" ARG VLLM_PATCHED_PACKAGE_VERSION="0.8.4.post1"
ARG VLLM_MAX_JOBS=4 ARG VLLM_MAX_JOBS=4
RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \ RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \
--mount=type=cache,target=/root/.cache/uv \ --mount=type=cache,target=/root/.cache/uv \
......
...@@ -101,7 +101,7 @@ VLLM_BASE_IMAGE_TAG="25.03-cuda12.8-devel-ubuntu24.04" ...@@ -101,7 +101,7 @@ VLLM_BASE_IMAGE_TAG="25.03-cuda12.8-devel-ubuntu24.04"
NONE_BASE_IMAGE="ubuntu" NONE_BASE_IMAGE="ubuntu"
NONE_BASE_IMAGE_TAG="24.04" NONE_BASE_IMAGE_TAG="24.04"
NIXL_COMMIT=d247e88c72db75dc00e4e37aa21ed8d99e60c27d NIXL_COMMIT=78695c2900cd7fff506764377386592dfc98e87e
NIXL_REPO=ai-dynamo/nixl.git NIXL_REPO=ai-dynamo/nixl.git
NO_CACHE="" NO_CACHE=""
......
...@@ -1007,7 +1007,7 @@ dependencies = [ ...@@ -1007,7 +1007,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-engine-python" name = "dynamo-engine-python"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-openai", "async-openai",
...@@ -1028,7 +1028,7 @@ dependencies = [ ...@@ -1028,7 +1028,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-llm" name = "dynamo-llm"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"akin", "akin",
"anyhow", "anyhow",
...@@ -1083,7 +1083,7 @@ dependencies = [ ...@@ -1083,7 +1083,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-py3" name = "dynamo-py3"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"dynamo-engine-python", "dynamo-engine-python",
"dynamo-llm", "dynamo-llm",
...@@ -1104,7 +1104,7 @@ dependencies = [ ...@@ -1104,7 +1104,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-runtime" name = "dynamo-runtime"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-nats", "async-nats",
......
...@@ -19,7 +19,7 @@ ...@@ -19,7 +19,7 @@
[package] [package]
name = "dynamo-py3" name = "dynamo-py3"
version = "0.2.0" version = "0.2.1"
edition = "2021" edition = "2021"
authors = ["NVIDIA"] authors = ["NVIDIA"]
license = "Apache-2.0" license = "Apache-2.0"
......
...@@ -623,7 +623,7 @@ dependencies = [ ...@@ -623,7 +623,7 @@ dependencies = [
[[package]] [[package]]
name = "dynamo-runtime" name = "dynamo-runtime"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-nats", "async-nats",
...@@ -994,7 +994,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" ...@@ -994,7 +994,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
[[package]] [[package]]
name = "hello_world" name = "hello_world"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"dynamo-runtime", "dynamo-runtime",
] ]
...@@ -2306,7 +2306,7 @@ dependencies = [ ...@@ -2306,7 +2306,7 @@ dependencies = [
[[package]] [[package]]
name = "service_metrics" name = "service_metrics"
version = "0.2.0" version = "0.2.1"
dependencies = [ dependencies = [
"dynamo-runtime", "dynamo-runtime",
"futures", "futures",
......
...@@ -21,7 +21,7 @@ members = [ ...@@ -21,7 +21,7 @@ members = [
resolver = "3" resolver = "3"
[workspace.package] [workspace.package]
version = "0.2.0" version = "0.2.1"
edition = "2021" edition = "2021"
authors = ["NVIDIA"] authors = ["NVIDIA"]
license = "Apache-2.0" license = "Apache-2.0"
......
...@@ -15,7 +15,7 @@ ...@@ -15,7 +15,7 @@
[project] [project]
name = "ai-dynamo" name = "ai-dynamo"
version = "0.2.0" version = "0.2.1"
description = "Distributed Inference Framework" description = "Distributed Inference Framework"
readme = "README.md" readme = "README.md"
authors = [ authors = [
...@@ -29,7 +29,7 @@ dependencies = [ ...@@ -29,7 +29,7 @@ dependencies = [
"bentoml==1.4.8", "bentoml==1.4.8",
"types-psutil==7.0.0.20250218", "types-psutil==7.0.0.20250218",
"kubernetes==32.0.1", "kubernetes==32.0.1",
"ai-dynamo-runtime==0.2.0", "ai-dynamo-runtime==0.2.1",
"fastapi==0.115.6", "fastapi==0.115.6",
"distro", "distro",
"typer", "typer",
......
...@@ -40,21 +40,21 @@ If you are using a **GPU**, the following GPU models and architectures are suppo ...@@ -40,21 +40,21 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
### Runtime Dependency ### Runtime Dependency
| **Python Package** | **Version** | glibc version | CUDA Version | | **Python Package** | **Version** | glibc version | CUDA Version |
|--------------------|---------------|----------------------|--------------| |--------------------|---------------|----------------------|--------------|
| ai-dynamo | 0.2.0 | >=2.28 | | | ai-dynamo | 0.2.1 | >=2.28 | |
| ai-dynamo-runtime | 0.2.0 | >=2.28 | | | ai-dynamo-runtime | 0.2.1 | >=2.28 | |
| ai-dynamo-vllm | 0.8.4* | >=2.28 (recommended) | | | ai-dynamo-vllm | 0.8.4.post1* | >=2.28 (recommended) | |
| NIXL | 0.2.0 | >=2.27 | >=11.8 | | NIXL | 0.2.1 | >=2.27 | >=11.8 |
### Build Dependency ### Build Dependency
| **Build Dependency** | **Version** | | **Build Dependency** | **Version** |
|----------------------|-------------| |----------------------|-------------|
| **Base Container** | [25.03](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda-dl-base/tags) | | **Base Container** | [25.03](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda-dl-base/tags) |
| **ai-dynamo-vllm** |0.8.4* | | **ai-dynamo-vllm** |0.8.4.post1* |
| **TensorRT-LLM** | 0.19.0** | | **TensorRT-LLM** | 0.19.0** |
| **NIXL** | 0.2.0 | | **NIXL** | 0.2.1 |
> **Note**: > **Note**:
> - *ai-dynamo-vllm v0.8.4 is a customized patch of v0.8.4 from vLLM. > - *ai-dynamo-vllm v0.8.4.post1 is a customized patch of v0.8.4 from vLLM.
> - **The specific version of TensorRT-LLM (planned v0.19.0) that will be supported by Dynamo is subject to change. > - **The specific version of TensorRT-LLM (planned v0.19.0) that will be supported by Dynamo is subject to change.
......
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