Removes source compilation of nixl dependency (vllm-project#24874)

Signed-off-by: bbartels <[email protected]>
Signed-off-by: Benjamin Bartels <[email protected]>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Daniele <[email protected]>
Signed-off-by: xuebwang-amd <[email protected]>

Author: 3 people

docker/Dockerfile

@@ -283,6 +283,10 @@ WORKDIR /vllm-workspace
 ENV DEBIAN_FRONTEND=noninteractive
 ARG TARGETPLATFORM
 
+ARG GDRCOPY_CUDA_VERSION=12.8
+# Keep in line with FINAL_BASE_IMAGE
+ARG GDRCOPY_OS_VERSION=Ubuntu22_04
+
 SHELL ["/bin/bash", "-c"]
 
 ARG DEADSNAKES_MIRROR_URL
@@ -441,13 +445,21 @@ COPY tools/install_deepgemm.sh /tmp/install_deepgemm.sh
 RUN --mount=type=cache,target=/root/.cache/uv \
     VLLM_DOCKER_BUILD_CONTEXT=1 /tmp/install_deepgemm.sh --cuda-version "${CUDA_VERSION}" ${DEEPGEMM_GIT_REF:+--ref "$DEEPGEMM_GIT_REF"} 
 
-# Install EP kernels(pplx-kernels and DeepEP), NixL
+COPY tools/install_gdrcopy.sh install_gdrcopy.sh
+RUN set -eux; \
+    case "${TARGETPLATFORM}" in \
+      linux/arm64) UUARCH="aarch64" ;; \
+      linux/amd64) UUARCH="x64" ;; \
+      *) echo "Unsupported TARGETPLATFORM: ${TARGETPLATFORM}" >&2; exit 1 ;; \
+    esac; \
+    ./install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}"; \
+    rm ./install_gdrcopy.sh
+
+# Install EP kernels(pplx-kernels and DeepEP)
 COPY tools/ep_kernels/install_python_libraries.sh install_python_libraries.sh
-COPY tools/install_nixl.sh install_nixl.sh
 ENV CUDA_HOME=/usr/local/cuda
 RUN export TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-9.0a+PTX}" \
-    && bash install_python_libraries.sh \
-    && bash install_nixl.sh --force
+    && bash install_python_libraries.sh
 
 #################### vLLM installation IMAGE ####################
 

docs/serving/expert_parallel_deployment.md

@@ -10,7 +10,7 @@ Before using EP, you need to install the necessary dependencies. We are actively
 
 1. **Install DeepEP and pplx-kernels**: Set up host environment following vLLM's guide for EP kernels [here](gh-file:tools/ep_kernels).
 2. **Install DeepGEMM library**: Follow the [official instructions](https://github.com/deepseek-ai/DeepGEMM#installation).
-3. **For disaggregated serving**: Install UCX and NIXL following the [script](gh-file:tools/install_nixl.sh).
+3. **For disaggregated serving**: Install `gdrcopy` by running the [`install_gdrcopy.sh`](gh-file:tools/install_gdrcopy.sh) script (e.g., `install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "12.8" "x64"`). You can find available OS versions [here](https://developer.download.nvidia.com/compute/redist/gdrcopy/CUDA%2012.8/).
 
 ### Backend Selection Guide
 
@@ -191,7 +191,7 @@ For production deployments requiring strict SLA guarantees for time-to-first-tok
 
 ### Setup Steps
 
-1. **Install KV Connector**: Install NIXL using the [installation script](gh-file:tools/install_nixl.sh)
+1. **Install gdrcopy/ucx/nixl**: For maximum performance, run the [install_gdrcopy.sh](gh-file:tools/install_gdrcopy.sh) script to install `gdrcopy` (e.g., `install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "12.8" "x64"`). You can find available OS versions [here](https://developer.download.nvidia.com/compute/redist/gdrcopy/CUDA%2012.8/). If `gdrcopy` is not installed, things will still work with a plain `pip install nixl`, just with lower performance. `nixl` and `ucx` are installed as dependencies via pip.
 
 2. **Configure Both Instances**: Add this flag to both prefill and decode instances `--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}`
 

requirements/kv_connectors.txt

@@ -1 +1,2 @@
-lmcache
+lmcache
+nixl >= 0.5.1 # Required for disaggregated prefill

tools/install_gdrcopy.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Usage: install_gdrcopy.sh <GDRCOPY_OS_VERSION> <GDRCOPY_CUDA_VERSION> <uuarch>
+# uuarch must be "x64" or "aarch64"
+# Optional: set GDRCOPY_VERSION to override the libgdrapi package version (default: 2.5.1-1)
+# Requires: curl, apt-get, root privileges
+if [[ $(id -u) -ne 0 ]]; then
+  echo "Must be run as root" >&2
+  
+  exit 1
+fi
+if [[ $# -ne 3 ]]; then
+  echo "Usage: $0 <GDRCOPY_OS_VERSION> <GDRCOPY_CUDA_VERSION> <uuarch(x64|aarch64)>" >&2
+  exit 1
+fi
+
+OS_VER="$1"
+CUDA_VER="$2"
+UUARCH_RAW="$3"
+
+# Normalize/validate arch
+case "${UUARCH_RAW,,}" in
+  aarch64|arm64)
+    URL_ARCH="aarch64"
+    DEB_ARCH="arm64"
+    ;;
+  x64|x86_64|amd64)
+    URL_ARCH="x64"
+    DEB_ARCH="amd64"
+    ;;
+  *)
+    echo "Unsupported uuarch: ${UUARCH_RAW}. Use 'x64' or 'aarch64'." >&2
+    exit 1
+    ;;
+esac
+
+OS_VER_LOWER="$(tr '[:upper:]' '[:lower:]' <<<"$OS_VER")"
+GDRCOPY_PKG_VER="${GDRCOPY_VERSION:-2.5.1-1}"
+
+DEB_NAME="libgdrapi_${GDRCOPY_PKG_VER}_${DEB_ARCH}.${OS_VER}.deb"
+BASE_URL="https://developer.download.nvidia.com/compute/redist/gdrcopy"
+URL="${BASE_URL}/CUDA%20${CUDA_VER}/${OS_VER_LOWER}/${URL_ARCH}/${DEB_NAME}"
+
+echo "Downloading: ${URL}"
+TMPDIR="$(mktemp -d)"
+trap 'rm -rf "${TMPDIR}"' EXIT
+
+curl -fSL "${URL}" -o "${TMPDIR}/${DEB_NAME}"
+
+export DEBIAN_FRONTEND=noninteractive
+apt-get update
+apt-get install -y "${TMPDIR}/${DEB_NAME}"
+apt-get clean
+rm -rf /var/lib/apt/lists/*
+
+echo "Installed ${DEB_NAME}"