Skip to content

GitLab

Unverified Commit 5fa4cdda authored by Anant Sharma's avatar Anant Sharma Committed by GitHub
Browse files

chore: update nixl to 0.4.0 release (#1860)

parent 8cd94119
Show whitespace changes
Inline Side-by-side
Showing with 9 additions and 9 deletions
Cargo.lock
View file @ 5fa4cdda
...@@ -4308,9 +4308,9 @@ dependencies = [ ...@@ -4308,9 +4308,9 @@ dependencies = [
[[package]] [[package]]
name = "nixl-sys" name = "nixl-sys"
version = "0.3.1" version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55f74dbb6d0e18023aa6ce29563114b848f23c3c2f9d663383eb3cd590a1eacc" checksum = "97f621270fd1ed8af5a8028a1945e6f7e612a38836ce82b720fe54222739df3c"
dependencies = [ dependencies = [
"bindgen 0.71.1", "bindgen 0.71.1",
"cc", "cc",
......
container/build.sh
View file @ 5fa4cdda
...@@ -114,7 +114,7 @@ SGLANG_BASE_IMAGE_TAG="25.01-cuda12.8-devel-ubuntu24.04" ...@@ -114,7 +114,7 @@ SGLANG_BASE_IMAGE_TAG="25.01-cuda12.8-devel-ubuntu24.04"
VLLM_V1_BASE_IMAGE="nvcr.io/nvidia/cuda-dl-base" VLLM_V1_BASE_IMAGE="nvcr.io/nvidia/cuda-dl-base"
VLLM_V1_BASE_IMAGE_TAG="25.01-cuda12.8-devel-ubuntu24.04" VLLM_V1_BASE_IMAGE_TAG="25.01-cuda12.8-devel-ubuntu24.04"
NIXL_COMMIT=3503658e71143b56f9d5b1b440d84a94b9c41af8 NIXL_COMMIT=3c47a48955e6f96bd5d4fb43a9d80bb64722f8e4
NIXL_REPO=ai-dynamo/nixl.git NIXL_REPO=ai-dynamo/nixl.git
NIXL_UCX_EFA_REF=7ec95b95e524a87e81cac92f5ca8523e3966b16b NIXL_UCX_EFA_REF=7ec95b95e524a87e81cac92f5ca8523e3966b16b
......
docs/support_matrix.md
View file @ 5fa4cdda
...@@ -73,7 +73,7 @@ If you are using a **GPU**, the following GPU models and architectures are suppo ...@@ -73,7 +73,7 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
| ai-dynamo | 0.3.2 | >=2.28 | | | ai-dynamo | 0.3.2 | >=2.28 | |
| ai-dynamo-runtime | 0.3.2 | >=2.28 (Python 3.12 has known issues)| | | ai-dynamo-runtime | 0.3.2 | >=2.28 (Python 3.12 has known issues)| |
| ai-dynamo-vllm | 0.8.4.post4¹ | >=2.28 (recommended) | | | ai-dynamo-vllm | 0.8.4.post4¹ | >=2.28 (recommended) | |
| NIXL | 0.3.1 | >=2.27 | >=11.8 | | NIXL | 0.4.0 | >=2.27 | >=11.8 |
### Build Dependency ### Build Dependency
...@@ -82,7 +82,7 @@ If you are using a **GPU**, the following GPU models and architectures are suppo ...@@ -82,7 +82,7 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
| **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.post4¹ | | **ai-dynamo-vllm** | 0.8.4.post4¹ |
| **TensorRT-LLM** | 1.0.0rc² | | **TensorRT-LLM** | 1.0.0rc² |
| **NIXL** | 0.3.1 | | **NIXL** | 0.4.0 |
> [!Important] > [!Important]
> ¹ ai-dynamo-vllm `v0.8.4.post4` 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.
......
lib/bindings/python/Cargo.lock
View file @ 5fa4cdda
...@@ -3934,9 +3934,9 @@ dependencies = [ ...@@ -3934,9 +3934,9 @@ dependencies = [
[[package]] [[package]]
name = "nixl-sys" name = "nixl-sys"
version = "0.3.1" version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55f74dbb6d0e18023aa6ce29563114b848f23c3c2f9d663383eb3cd590a1eacc" checksum = "97f621270fd1ed8af5a8028a1945e6f7e612a38836ce82b720fe54222739df3c"
dependencies = [ dependencies = [
"bindgen 0.71.1", "bindgen 0.71.1",
"cc", "cc",
......
lib/llm/Cargo.toml
View file @ 5fa4cdda
...@@ -85,7 +85,7 @@ rayon = "1" ...@@ -85,7 +85,7 @@ rayon = "1"
dialoguer = { version = "0.11", default-features = false, features = ["editor", "history"] } dialoguer = { version = "0.11", default-features = false, features = ["editor", "history"] }
# block_manager # block_manager
nixl-sys = {version = "0.3.1", optional = true } nixl-sys = {version = "0.4.0", optional = true }
cudarc = { version = "0.16.2", features = ["cuda-12020"], optional = true } cudarc = { version = "0.16.2", features = ["cuda-12020"], optional = true }
ndarray = { version = "0.16", optional = true } ndarray = { version = "0.16", optional = true }
nix = { version = "0.26", optional = true } nix = { version = "0.26", optional = true }
......
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