Skip to content

GitLab

Unverified Commit 99e67e60 authored by Anant Sharma's avatar Anant Sharma Committed by GitHub
Browse files

chore: update dynamo and nixl versions for 0.3.1 (#1517)

parent 50afb811
Hide whitespace changes
Inline Side-by-side
Showing with 41 additions and 41 deletions
Cargo.lock
View file @ 99e67e60
......@@ -1555,7 +1555,7 @@ dependencies = [
[[package]]
name = "dynamo-engine-llamacpp"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"async-stream",
"dynamo-llm",
......@@ -1567,7 +1567,7 @@ dependencies = [
[[package]]
name = "dynamo-engine-mistralrs"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"async-openai",
......@@ -1586,7 +1586,7 @@ dependencies = [
[[package]]
name = "dynamo-llm"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"akin",
"aligned-vec",
......@@ -1658,7 +1658,7 @@ dependencies = [
[[package]]
name = "dynamo-run"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"async-openai",
......@@ -1687,7 +1687,7 @@ dependencies = [
[[package]]
name = "dynamo-runtime"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"assert_matches",
......@@ -1736,7 +1736,7 @@ dependencies = [
[[package]]
name = "dynamo-tokens"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"bytemuck",
"derive-getters",
......@@ -2747,7 +2747,7 @@ dependencies = [
[[package]]
name = "http"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"clap",
"dynamo-llm",
......@@ -3365,7 +3365,7 @@ checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
[[package]]
name = "libdynamo_llm"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"async-once-cell",
......@@ -3478,7 +3478,7 @@ dependencies = [
[[package]]
name = "llmctl"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"clap",
......@@ -3678,7 +3678,7 @@ dependencies = [
[[package]]
name = "metrics"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"axum 0.6.20",
"clap",
......@@ -4085,9 +4085,9 @@ dependencies = [
[[package]]
name = "nixl-sys"
version = "0.3.0-rc.2"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a1727039c315bf41aeadcdbea02522b8a3df69a77bd732996243502a5fb6f07"
checksum = "c5ed1b2b73a39516cb082cc2e0c8cf5fa9aadf7364b3b7851f43fbcda70566ee"
dependencies = [
"bindgen 0.71.1",
"cc",
......@@ -5346,7 +5346,7 @@ dependencies = [
[[package]]
name = "router"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"clap",
"dynamo-llm",
......
Cargo.toml
View file @ 99e67e60
......@@ -28,7 +28,7 @@ members = [
resolver = "3"
[workspace.package]
version = "0.3.0"
version = "0.3.1"
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 = "0.3.0" }
dynamo-llm = { path = "lib/llm", version = "0.3.0" }
dynamo-tokens = { path = "lib/tokens", version = "0.3.0" }
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" }
# External dependencies
anyhow = { version = "1" }
......
container/Dockerfile.vllm
View file @ 99e67e60
......@@ -178,7 +178,7 @@ 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.post2"
ARG VLLM_PATCHED_PACKAGE_VERSION="0.8.4.post3"
ARG VLLM_MAX_JOBS=4
RUN --mount=type=bind,source=./container/deps/,target=/tmp/deps \
--mount=type=cache,target=/root/.cache/uv \
......
container/build.sh
View file @ 99e67e60
......@@ -109,7 +109,7 @@ NONE_BASE_IMAGE_TAG="24.04"
SGLANG_BASE_IMAGE="nvcr.io/nvidia/cuda-dl-base"
SGLANG_BASE_IMAGE_TAG="25.01-cuda12.8-devel-ubuntu24.04"
NIXL_COMMIT=f531404be4866d85ed618b3baf4008c636798d63
NIXL_COMMIT=16348080f5bdeb9fe6058a23be140cec020ef3f3
NIXL_REPO=ai-dynamo/nixl.git
NIXL_UCX_EFA_REF=7ec95b95e524a87e81cac92f5ca8523e3966b16b
......
docs/support_matrix.md
View file @ 99e67e60
......@@ -68,24 +68,24 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
### Runtime Dependency
| **Python Package** | **Version** | glibc version | CUDA Version |
| :----------------- | :------------ | :------------------- | :----------- |
| ai-dynamo | 0.3.0 | >=2.28 | |
| ai-dynamo-runtime | 0.3.0 | >=2.28 | |
| ai-dynamo-vllm | 0.8.4.post2¹ | >=2.28 (recommended) | |
| NIXL | 0.3.0 | >=2.27 | >=11.8 |
| **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) | |
| 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.post2¹ |
| **TensorRT-LLM** | 0.19.0² |
| **NIXL** | 0.3.0 |
| **ai-dynamo-vllm** | 0.8.4.post3¹ |
| **TensorRT-LLM** | 0.21.0rc² |
| **NIXL** | 0.3.1 |
> [!Important]
> ¹ ai-dynamo-vllm `v0.8.4.post2` is a customized patch of `v0.8.4` from vLLM.
> ¹ ai-dynamo-vllm `v0.8.4.post3` is a customized patch of `v0.8.4` from vLLM.
>
> ² Specific versions of TensorRT-LLM supported by Dynamo are subject to change.
......
lib/bindings/python/Cargo.lock
View file @ 99e67e60
......@@ -1092,7 +1092,7 @@ dependencies = [
[[package]]
name = "dynamo-llm"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"akin",
"anyhow",
......@@ -1155,7 +1155,7 @@ dependencies = [
[[package]]
name = "dynamo-py3"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"async-openai",
......@@ -1180,7 +1180,7 @@ dependencies = [
[[package]]
name = "dynamo-runtime"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"async-nats",
......@@ -2810,9 +2810,9 @@ dependencies = [
[[package]]
name = "nixl-sys"
version = "0.3.0-rc.2"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a1727039c315bf41aeadcdbea02522b8a3df69a77bd732996243502a5fb6f07"
checksum = "c5ed1b2b73a39516cb082cc2e0c8cf5fa9aadf7364b3b7851f43fbcda70566ee"
dependencies = [
"bindgen",
"cc",
......
lib/bindings/python/Cargo.toml
View file @ 99e67e60
......@@ -19,7 +19,7 @@
[package]
name = "dynamo-py3"
version = "0.3.0"
version = "0.3.1"
edition = "2021"
authors = ["NVIDIA"]
license = "Apache-2.0"
......
lib/runtime/examples/Cargo.lock
View file @ 99e67e60
......@@ -623,7 +623,7 @@ dependencies = [
[[package]]
name = "dynamo-runtime"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"anyhow",
"async-nats",
......@@ -994,7 +994,7 @@ checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
[[package]]
name = "hello_world"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"dynamo-runtime",
]
......@@ -2306,7 +2306,7 @@ dependencies = [
[[package]]
name = "service_metrics"
version = "0.3.0"
version = "0.3.1"
dependencies = [
"dynamo-runtime",
"futures",
......
lib/runtime/examples/Cargo.toml
View file @ 99e67e60
......@@ -21,7 +21,7 @@ members = [
resolver = "3"
[workspace.package]
version = "0.3.0"
version = "0.3.1"
edition = "2021"
authors = ["NVIDIA"]
license = "Apache-2.0"
......
pyproject.toml
View file @ 99e67e60
......@@ -15,7 +15,7 @@
[project]
name = "ai-dynamo"
version = "0.3.0"
version = "0.3.1"
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==0.3.0",
"ai-dynamo-runtime==0.3.1",
"fastapi==0.115.6",
"distro",
# filelock: required by planner
......
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