Merge origin/main into cheese-head/rust-param-bindings

- Resolved merge conflict in src/bindings/rust/src/lib.rs
- Applied clang-format to C++ files
- All tests and formatting checks should pass

Author: cheese-head

.ci/dockerfiles/Dockerfile.gpu_test

@@ -3,7 +3,7 @@
 # This Dockerfile creates a GPU-enabled test environment for NIXL (NVIDIA I/O eXchange Layer)
 # development and testing. It provides a containerized environment with:
 #
-# - NVIDIA PyTorch base image with CUDA support
+# - NVIDIA cuda-dl-base image with CUDA support
 # - Non-root user setup for security
 # - Sudo access for package installation and system configuration
 # - Optimized for CI/CD pipeline testing
@@ -13,7 +13,7 @@
 #   docker run --gpus all --privileged -it nixl-gpu-test
 #
 # Build arguments:
-#   BASE_IMAGE: Base NVIDIA PyTorch image (default: nvcr.io/nvidia/pytorch:25.02-py3)
+#   BASE_IMAGE: Base NVIDIA cuda-dl-base image (default: nvcr.io/nvidia/cuda-dl-base:25.06-cuda12.9-devel-ubuntu24.04)
 #   _UID: User ID for the non-root user (default: 148069)
 #   _GID: Group ID for the user (default: 30)
 #   _LOGIN: Username (default: svc-nixl)
@@ -22,7 +22,7 @@
 #   WORKSPACE: Workspace directory path
 #
 
-ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:25.02-py3
+ARG BASE_IMAGE=nvcr.io/nvidia/cuda-dl-base:25.06-cuda12.9-devel-ubuntu24.04
 
 FROM ${BASE_IMAGE}
 
@@ -32,7 +32,7 @@ ARG _GID=30
 ARG _LOGIN=svc-nixl
 ARG _GROUP=hardware
 ARG _HOME=/home/$_LOGIN
-ARG WORKSPACE
+ARG WORKSPACE=/workspace
 
 # Labels for documentation
 LABEL maintainer="NVIDIA NIXL Team"
@@ -41,7 +41,7 @@ LABEL version="1.0"
 
 # Update package list and install required packages in one layer
 RUN apt-get update && \
-    apt-get install -y sudo \
+    apt-get install -y sudo python3 python3-pip \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
@@ -59,6 +59,9 @@ RUN mkdir -p /etc/sudoers.d && \
     chmod 440 /etc/sudoers.d/${_LOGIN} && \
     chown root:root /etc/sudoers.d/${_LOGIN}
 
+# Create and set permissions for workspace directory
+RUN mkdir -p ${WORKSPACE} && chmod 777 ${WORKSPACE}
+
 # Copy workspace into container (workaround for files disappearing from workspace)
 COPY --chown="${_UID}":"${_GID}" . ${WORKSPACE}
 

.ci/docs/setup_nvidia_gpu_with_rdma_support_on_ubuntu.md

@@ -93,10 +93,16 @@ GDS is bundled with CUDA ≥11.4 but requires explicit enabling:
 
 ```bash
 sudo echo "options nvidia NVreg_EnableGpuDirectStorage=1" > /etc/modprobe.d/nvidia-gds.conf
+
+# Configure PeerMappingOverride for GPU-Initiated RDMA support
+sudo echo "options nvidia NVreg_RegistryDwords=\"PeerMappingOverride=1;\"" > /etc/modprobe.d/nvidia.conf
+
 sudo update-initramfs -u
 sudo reboot
 ```
 
+The `PeerMappingOverride=1` option is required for proper GPU peer-to-peer communication in RDMA environments.
+
 ### 6. **Enable Kernel Modules at Boot**
 
 Add required modules to `/etc/modules`:
@@ -131,7 +137,7 @@ sudo nvidia-ctk runtime configure --runtime=docker
 sudo systemctl restart docker
 ```
 
-Verify GPU access in containers using `docker run --gpus all nvcr.io/nvidia/pytorch:25.02-py3 nvidia-smi`[^1_3].
+Verify GPU access in containers using `docker run --gpus all nvcr.io/nvidia/cuda-dl-base:25.06-cuda12.9-devel-ubuntu24.04 nvidia-smi`[^1_3].
 
 ### 9. **Validation and Troubleshooting**
 

.ci/jenkins/lib/build-container-matrix.yaml

@@ -31,7 +31,6 @@ env:
   REGISTRY_REPO: "sw-nbu-swx-nixl-docker-local/verification"
   LOCAL_TAG_BASE: "nixl-ci:build-"
   MAIL_FROM: "[email protected]"
-  NPROC: "16"
 
 taskName: "${BUILD_TARGET}/${arch}/${axis_index}"
 
@@ -89,6 +88,7 @@ steps:
         --base-image-tag "${BASE_IMAGE_TAG}" \
         --tag "${LOCAL_TAG_BASE}${arch}" \
         --arch "${arch}" \
+        --build-type debug \
         --no-cache
 
   - name: Add Version Info
@@ -175,7 +175,7 @@ steps:
         echo "benchmark/nixlbench/contrib/build.sh --base-image ${BASE_IMAGE} --base-image-tag ${BASE_IMAGE_TAG} --tag local-test-tag --arch ${arch} --no-cache --nixl \$WORKSPACE --ucx \$WORKSPACE/ucx-src"
       else
         echo "export UCX_REF=${UCX_VERSION}"
-        echo "contrib/build-container.sh --base-image ${BASE_IMAGE} --base-image-tag ${BASE_IMAGE_TAG} --tag local-test-tag --arch ${arch} --no-cache"
+        echo "contrib/build-container.sh --base-image ${BASE_IMAGE} --base-image-tag ${BASE_IMAGE_TAG} --tag local-test-tag --arch ${arch} --build-type debug --no-cache"
       fi
 
 pipeline_stop:

.ci/jenkins/lib/build-matrix.yaml

@@ -6,7 +6,7 @@
 # Key Components:
 # - Job Configuration: Defines timeout, failure behavior, and Kubernetes resources
 # - Docker Images: Specifies the container images used for different build stages
-#   - PyTorch images (24.10 and 25.02) for building and testing
+#   - cuda-dl-base images (25.06 for Ubuntu 24.04, 24.10 for Ubuntu 22.04) for building and testing
 #   - Podman image for container builds
 # - Matrix Axes: Defines build variations (currently x86_64 architecture)
 # - Build Steps: Sequential steps for building, testing, and container creation
@@ -34,8 +34,8 @@ kubernetes:
   requests: "{memory: 8Gi, cpu: 8000m}"
 
 runs_on_dockers:
-  - { name: "ubuntu24.04-pytorch", url: "nvcr.io/nvidia/pytorch:25.02-py3" }
-  - { name: "ubuntu22.04-pytorch", url: "nvcr.io/nvidia/pytorch:24.10-py3" }
+  - { name: "ubuntu24.04-cuda-dl-base", url: "nvcr.io/nvidia/cuda-dl-base:25.06-cuda12.9-devel-ubuntu24.04" }
+  - { name: "ubuntu22.04-cuda-dl-base", url: "nvcr.io/nvidia/cuda-dl-base:24.10-cuda12.6-devel-ubuntu22.04" }
   - { name: "podman-v5.0.2", url: "quay.io/podman/stable:v5.0.2", category: 'tool', privileged: true }
 
 matrix:
@@ -47,17 +47,12 @@ matrix:
 env:
   NIXL_INSTALL_DIR: /opt/nixl
   TEST_TIMEOUT: 30
-  NPROC: "16"
   UCX_TLS: "^shm"
 
 steps:
   - name: Build
     parallel: false
     run: |
-      if [[ "${name}" == *"ubuntu22.04"* ]]; then
-        # distro's meson version is too old project requires >= 0.64.0
-        pip3 install meson
-      fi
       .gitlab/build.sh ${NIXL_INSTALL_DIR}
 
   - name: Test CPP
@@ -94,4 +89,4 @@ steps:
       ln -sfT $(type -p podman) /usr/bin/docker
       # install git for building container image
       yum install -y git
-      contrib/build-container.sh --no-cache
+      contrib/build-container.sh --build-type debug --no-cache

.ci/jenkins/lib/test-matrix.yaml

@@ -30,18 +30,22 @@ runs_on_agents:
 matrix:
   axes:
     image:
-      - nvcr.io/nvidia/pytorch:25.02-py3
+      - nvcr.io/nvidia/cuda-dl-base:25.06-cuda12.9-devel-ubuntu24.04
     arch:
       - x86_64
+    ucx_version:
+      - master
+      - v1.20.x
 
-taskName: "${name}/${arch}/${axis_index}"
+taskName: "${name}/${arch}/ucx-${ucx_version}/${axis_index}"
 
 env:
-  INSTALL_DIR: ${WORKSPACE}/nixl_install
-  UCX_VERSION: v1.19.0
-  NPROC: "16"
+  CONTAINER_WORKSPACE: /workspace
+  INSTALL_DIR: ${CONTAINER_WORKSPACE}/nixl_install
   # Manual timeout - ci-demo doesn't handle docker exec
   TEST_TIMEOUT: 30
+  # NPROC for bare-metal: containers see all host CPUs, need to limit parallelism
+  NPROC: 16
 
 steps:
   - name: Get Environment Info
@@ -71,7 +75,7 @@ steps:
   - name: Build GPU Test Environment
     parallel: false
     run: |
-      docker build -t "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" -f .ci/dockerfiles/Dockerfile.gpu_test --build-arg BASE_IMAGE=${image} --build-arg WORKSPACE=${WORKSPACE} .
+      docker build -t "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" -f .ci/dockerfiles/Dockerfile.gpu_test --build-arg BASE_IMAGE=${image} --build-arg WORKSPACE=${CONTAINER_WORKSPACE} .
     onfail: docker image rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
 
   - name: Run GPU Test Environment
@@ -93,39 +97,41 @@ steps:
   - name: Build
     parallel: false
     run: |
-      docker exec -w ${WORKSPACE} -e UCX_VERSION=${UCX_VERSION} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/build.sh ${INSTALL_DIR}"
+      set -ex
+      docker exec -w ${CONTAINER_WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c "UCX_VERSION=${ucx_version} .gitlab/build.sh ${INSTALL_DIR}"
+
     onfail: |
       docker rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
       docker image rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
 
   - name: Test CPP
     parallel: false
     run: |
-      timeout ${TEST_TIMEOUT}m docker exec -w ${WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_cpp.sh ${INSTALL_DIR}"
+      timeout ${TEST_TIMEOUT}m docker exec -w ${CONTAINER_WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_cpp.sh ${INSTALL_DIR}"
     onfail: |
       docker rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
       docker image rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
 
   - name: Test Python
     parallel: false
     run: |
-      timeout ${TEST_TIMEOUT}m docker exec -w ${WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_python.sh ${INSTALL_DIR}"
+      timeout ${TEST_TIMEOUT}m docker exec -w ${CONTAINER_WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_python.sh ${INSTALL_DIR}"
     onfail: |
       docker rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
       docker image rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
 
   - name: Test Nixlbench
     parallel: false
     run: |
-      timeout ${TEST_TIMEOUT}m docker exec -w ${WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_nixlbench.sh ${INSTALL_DIR}"
+      timeout ${TEST_TIMEOUT}m docker exec -w ${CONTAINER_WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_nixlbench.sh ${INSTALL_DIR}"
     onfail: |
       docker rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
       docker image rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
 
   - name: Test Rust
     parallel: false
     run: |
-      timeout ${TEST_TIMEOUT}m docker exec -w ${WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_rust.sh ${INSTALL_DIR}"
+      timeout ${TEST_TIMEOUT}m docker exec -w ${CONTAINER_WORKSPACE} "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}" /bin/bash -c ".gitlab/test_rust.sh ${INSTALL_DIR}"
     always: |
       docker rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"
       docker image rm -f "${JOB_BASE_NAME}-${BUILD_ID}-${axis_index}"

.ci/jenkins/pipeline/proj-jjb.yaml

@@ -269,18 +269,18 @@
       - string:
           name: "NIXL_VERSION"
           default: "{jjb_branch}"
-          description: "NIXL version to use (tag like 0.6.1, branch name, or commit hash)"
+          description: "NIXL version to use (tag like 0.7.1, branch name, or commit hash)"
       - string:
           name: "UCX_VERSION"
-          default: "v1.19.0"
-          description: "UCX version to use (tag like v1.19.0, branch name, or commit hash)"
+          default: "v1.20.x"
+          description: "UCX version to use (tag like v1.20.x, branch name, or commit hash)"
       - string:
           name: "BASE_IMAGE"
           default: "nvcr.io/nvidia/cuda-dl-base"
           description: "Base Docker image for the container build"
       - string:
           name: "BASE_IMAGE_TAG"
-          default: "25.03-cuda12.8-devel-ubuntu24.04"
+          default: "25.06-cuda12.9-devel-ubuntu24.04"
           description: "Tag for the base Docker image"
       - string:
           name: "TAG_SUFFIX"
@@ -294,7 +294,7 @@
           description: >
             Update the latest tag for this architecture.<br/>
             When enabled, also creates: <code>&lt;base-image-tag&gt;-&lt;arch&gt;-latest</code><br/>
-            Example: <code>25.03-cuda12.8-devel-ubuntu24.04-aarch64-latest</code><br/>
+            Example: <code>25.06-cuda12.9-devel-ubuntu24.04-aarch64-latest</code><br/>
       - string:
           name: "MAIL_TO"
           default: "[email protected]"

.ci/scripts/common.sh

@@ -78,6 +78,11 @@ max_gtest_port=$((tcp_port_max + gtest_offset))
 # Check if a GPU is present
 nvidia-smi -L | grep -q '^GPU' && HAS_GPU=true || HAS_GPU=false
 
+# Ensure CUDA_HOME is set if CUDA is installed (cuda-dl-base images don't set it by default)
+if [ -d "/usr/local/cuda" ] && [ -z "$CUDA_HOME" ]; then
+    export CUDA_HOME=/usr/local/cuda
+fi
+
 if $HAS_GPU && test -d "$CUDA_HOME"
 then
     UCX_CUDA_BUILD_ARGS="--with-cuda=${CUDA_HOME}"
@@ -89,3 +94,24 @@ fi
 
 # Default to false, unless TEST_LIBFABRIC is set. AWS EFA tests must set it to true.
 export TEST_LIBFABRIC=${TEST_LIBFABRIC:-false}
+
+# Set default parallelism for make/ninja (can be overridden by NPROC env var)
+if [ -z "$NPROC" ]; then
+    # In containers, calculate based on memory limits to avoid OOM
+    if [[ -f /.dockerenv  ||  -f /run/.containerenv  ||  -n "${KUBERNETES_SERVICE_HOST}" ]]; then
+        if [ -f /sys/fs/cgroup/memory/memory.limit_in_bytes ]; then
+            limit=$(cat /sys/fs/cgroup/memory/memory.limit_in_bytes)
+        elif [ -f /sys/fs/cgroup/memory.max ]; then
+            limit=$(cat /sys/fs/cgroup/memory.max)
+        else
+            limit=$((4 * 1024 * 1024 * 1024))
+        fi
+        # Use 1 process per GB of memory, max 16
+        nproc=$((limit / (1024 * 1024 * 1024)))
+        nproc=$((nproc > 16 ? 16 : nproc))
+        nproc=$((nproc < 1 ? 1 : nproc))
+    else
+        nproc=$(nproc --all)
+    fi
+    export NPROC=$nproc
+fi

.gitlab/build.sh

@@ -27,9 +27,9 @@ INSTALL_DIR=$1
 UCX_INSTALL_DIR=$2
 EXTRA_BUILD_ARGS=${3:-""}
 # UCX_VERSION is the version of UCX to build override default with env variable.
-UCX_VERSION=${UCX_VERSION:-v1.19.0}
+UCX_VERSION=${UCX_VERSION:-v1.20.x}
 # LIBFABRIC_VERSION is the version of libfabric to build override default with env variable.
-LIBFABRIC_VERSION=${LIBFABRIC_VERSION:-v2.3.0}
+LIBFABRIC_VERSION=${LIBFABRIC_VERSION:-v1.21.0}
 # LIBFABRIC_INSTALL_DIR can be set via environment variable, defaults to INSTALL_DIR
 LIBFABRIC_INSTALL_DIR=${LIBFABRIC_INSTALL_DIR:-$INSTALL_DIR}
 
@@ -57,7 +57,9 @@ ARCH=$(uname -m)
 $SUDO rm -rf /usr/lib/cmake/grpc /usr/lib/cmake/protobuf
 
 $SUDO apt-get -qq update
-$SUDO apt-get -qq install -y curl \
+$SUDO apt-get -qq install -y python3-dev \
+                             python3-pip \
+                             curl \
                              wget \
                              libnuma-dev \
                              numactl \
@@ -101,6 +103,17 @@ $SUDO apt-get -qq install -y curl \
                              libhwloc-dev \
                              libcurl4-openssl-dev zlib1g-dev # aws-sdk-cpp dependencies
 
+# Ubuntu 22.04 specific setup
+if grep -q "Ubuntu 22.04" /etc/os-release 2>/dev/null; then
+    # Upgrade pip for '--break-system-packages' support
+    $SUDO pip3 install --upgrade pip
+
+    # Upgrade meson (distro version 0.61.2 is too old, project requires >= 0.64.0)
+    $SUDO pip3 install --upgrade meson
+    # Ensure pip3's meson takes precedence over apt's version
+    export PATH="$HOME/.local/bin:/usr/local/bin:$PATH"
+fi
+
 # Add DOCA repository and install packages
 ARCH_SUFFIX=$(if [ "${ARCH}" = "aarch64" ]; then echo "arm64"; else echo "amd64"; fi)
 MELLANOX_OS="$(. /etc/lsb-release; echo ${DISTRIB_ID}${DISTRIB_RELEASE} | tr A-Z a-z | tr -d .)"
@@ -122,6 +135,11 @@ chmod +x rustup-init
 ./rustup-init -y --default-toolchain 1.86.0
 export PATH="$HOME/.cargo/bin:$PATH"
 
+wget --tries=3 --waitretry=5 "https://astral.sh/uv/install.sh" -O install_uv.sh
+chmod +x install_uv.sh
+./install_uv.sh
+export PATH="$HOME/.local/bin:$PATH"
+
 curl -fSsL "https://github.com/openucx/ucx/tarball/${UCX_VERSION}" | tar xz
 ( \
   cd openucx-ucx* && \
@@ -167,7 +185,7 @@ rm "libfabric-${LIBFABRIC_VERSION#v}.tar.bz2"
   cd etcd-cpp-apiv3 && \
   mkdir build && cd build && \
   cmake .. && \
-  make -j"${NPROC:-$(nproc)}" && \
+  make -j"$NPROC" && \
   $SUDO make install && \
   $SUDO ldconfig \
 )
@@ -178,7 +196,7 @@ rm "libfabric-${LIBFABRIC_VERSION#v}.tar.bz2"
   mkdir aws_sdk_build && \
   cd aws_sdk_build && \
   cmake ../aws-sdk-cpp/ -DCMAKE_BUILD_TYPE=Release -DBUILD_ONLY="s3" -DENABLE_TESTING=OFF -DCMAKE_INSTALL_PREFIX=/usr/local && \
-  make -j"${NPROC:-$(nproc)}" && \
+  make -j"$NPROC" && \
   $SUDO make install
 )
 
@@ -209,12 +227,13 @@ export CMAKE_PREFIX_PATH="${INSTALL_DIR}:${CMAKE_PREFIX_PATH}"
 export UCX_TLS=^cuda_ipc
 
 # shellcheck disable=SC2086
-meson setup nixl_build --prefix=${INSTALL_DIR} -Ducx_path=${UCX_INSTALL_DIR} -Dbuild_docs=true -Drust=false ${EXTRA_BUILD_ARGS} -Dlibfabric_path="${LIBFABRIC_INSTALL_DIR}"
-ninja -C nixl_build && ninja -C nixl_build install
+meson setup nixl_build --prefix=${INSTALL_DIR} -Ducx_path=${UCX_INSTALL_DIR} -Dbuild_docs=true -Drust=false ${EXTRA_BUILD_ARGS} -Dlibfabric_path="${LIBFABRIC_INSTALL_DIR}" --buildtype=debug
+ninja -j"$NPROC" -C nixl_build && ninja -j"$NPROC" -C nixl_build install
+mkdir -p dist && cp nixl_build/src/bindings/python/nixl-meta/nixl-*.whl dist/
 
 # TODO(kapila): Copy the nixl.pc file to the install directory if needed.
 # cp ${BUILD_DIR}/nixl.pc ${INSTALL_DIR}/lib/pkgconfig/nixl.pc
 
 cd benchmark/nixlbench
 meson setup nixlbench_build -Dnixl_path=${INSTALL_DIR} -Dprefix=${INSTALL_DIR}
-ninja -C nixlbench_build && ninja -C nixlbench_build install
+ninja -j"$NPROC" -C nixlbench_build && ninja -j"$NPROC" -C nixlbench_build install