[CI] Implement uploading to PyPI and GitHub in the release pipeline, enable release image building for CUDA 13.0 (#31032)

(cherry picked from commit 8e61425ee6)

.buildkite/release-pipeline.yaml

@@ -1,6 +1,6 @@
 steps:
   # aarch64 + CUDA builds
-  - label: "Build arm64 wheel - CUDA 12.9"
+  - label: "Build wheel - aarch64 - CUDA 12.9"
     depends_on: ~
     id: build-wheel-arm64-cuda-12-9
     agents:
@@ -11,11 +11,11 @@ steps:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
-      - "bash .buildkite/scripts/upload-wheels.sh"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh"
     env:
       DOCKER_BUILDKIT: "1"
 
-  - label: "Build arm64 wheel - CUDA 13.0"
+  - label: "Build wheel - aarch64 - CUDA 13.0"
     depends_on: ~
     id: build-wheel-arm64-cuda-13-0
     agents:
@@ -26,12 +26,12 @@ steps:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04  --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
-      - "bash .buildkite/scripts/upload-wheels.sh manylinux_2_35"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
     env:
       DOCKER_BUILDKIT: "1"
 
   # aarch64 build
-  - label: "Build arm64 CPU wheel"
+  - label: "Build wheel - aarch64 - CPU"
     depends_on: ~
     id: build-wheel-arm64-cpu
     agents:
@@ -40,39 +40,39 @@ steps:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_BUILD_ACL=ON --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
-      - "bash .buildkite/scripts/upload-wheels.sh manylinux_2_35"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
     env:
       DOCKER_BUILDKIT: "1"
 
   # x86 + CUDA builds
-  - label: "Build wheel - CUDA 12.9"
+  - label: "Build wheel - x86_64 - CUDA 12.9"
     depends_on: ~
-    id: build-wheel-cuda-12-9
+    id: build-wheel-x86-cuda-12-9
     agents:
       queue: cpu_queue_postmerge
     commands:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
-      - "bash .buildkite/scripts/upload-wheels.sh manylinux_2_31"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_31"
     env:
       DOCKER_BUILDKIT: "1"
 
-  - label: "Build wheel - CUDA 13.0"
+  - label: "Build wheel - x86_64 - CUDA 13.0"
     depends_on: ~
-    id: build-wheel-cuda-13-0
+    id: build-wheel-x86-cuda-13-0
     agents:
       queue: cpu_queue_postmerge
     commands:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
-      - "bash .buildkite/scripts/upload-wheels.sh manylinux_2_35"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
     env:
       DOCKER_BUILDKIT: "1"
 
   # x86 CPU wheel build
-  - label: "Build x86 CPU wheel"
+  - label: "Build wheel - x86_64 - CPU"
     depends_on: ~
     id: build-wheel-x86-cpu
     agents:
@@ -81,12 +81,12 @@ steps:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_CPU_AVX512BF16=true --build-arg VLLM_CPU_AVX512VNNI=true --build-arg VLLM_CPU_AMXBF16=true --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
-      - "bash .buildkite/scripts/upload-wheels.sh manylinux_2_35"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
     env:
       DOCKER_BUILDKIT: "1"
 
-  # Build release images (12.9)
+  # Build release images (CUDA 12.9)
-  - label: "Build release image (x86)"
+  - label: "Build release image - x86_64 - CUDA 12.9"
     depends_on: ~
     id: build-release-image-x86
     agents:
@@ -99,7 +99,7 @@ steps:
       - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
       - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
 
-  - label: "Build release image (arm64)"
+  - label: "Build release image - aarch64 - CUDA 12.9"
     depends_on: ~
     id: build-release-image-arm64
     agents:
@@ -109,34 +109,92 @@ steps:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
       - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
 
-  # Add job to create multi-arch manifest
+  - label: "Create multi-arch manifest - CUDA 12.9"
-  - label: "Create multi-arch manifest"
     depends_on:
       - build-release-image-x86
       - build-release-image-arm64
     id: create-multi-arch-manifest
     agents:
-      queue: cpu_queue_postmerge
+      queue: small_cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
       - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 --amend"
       - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
 
-  - label: "Annotate release workflow"
+  - label: "Annotate release workflow - CUDA 12.9"
     depends_on:
       - create-multi-arch-manifest
     id: annotate-release-workflow
     agents:
-      queue: cpu_queue_postmerge
+      queue: small_cpu_queue_postmerge
     commands:
       - "bash .buildkite/scripts/annotate-release.sh"
 
+  - block: "Build CUDA 13.0 release images"
+    key: block-release-image-build-cuda-13-0
+    depends_on: ~
+
+  - label: "Build release image - x86_64 - CUDA 13.0"
+    depends_on: block-release-image-build-cuda-13-0
+    id: build-release-image-x86-cuda-13-0
+    agents:
+      queue: cpu_queue_postmerge
+    commands:
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130"
+      # re-tag to default image tag and push, just in case arm64 build fails
+      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"
+
+  - label: "Build release image - aarch64 - CUDA 13.0"
+    depends_on: block-release-image-build-cuda-13-0
+    id: build-release-image-arm64-cuda-13-0
+    agents:
+      queue: arm64_cpu_queue_postmerge
+    commands:
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130"
+
+  - label: "Create multi-arch manifest - CUDA 13.0"
+    depends_on:
+      - build-release-image-x86-cuda-13-0
+      - build-release-image-arm64-cuda-13-0
+    id: create-multi-arch-manifest-cuda-13-0
+    agents:
+      queue: small_cpu_queue_postmerge
+    commands:
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-cu130 --amend"
+      - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"
+
   - input: "Provide Release version here"
     id: input-release-version
     fields:
       - text: "What is the release version?"
         key: release-version
 
+  - block: "Confirm update release wheels to PyPI (experimental, use with caution)?"
+    key: block-upload-release-wheels
+    depends_on:
+      - input-release-version
+      - build-wheel-x86-cuda-12-9
+      - build-wheel-x86-cuda-13-0
+      - build-wheel-x86-cpu
+      - build-wheel-arm64-cuda-12-9
+      - build-wheel-arm64-cuda-13-0
+      - build-wheel-arm64-cpu
+
+  - label: "Upload release wheels to PyPI and GitHub"
+    depends_on:
+      - block-upload-release-wheels
+    id: upload-release-wheels
+    agents:
+      queue: small_cpu_queue_postmerge
+    commands:
+      - "bash .buildkite/scripts/upload-release-wheels.sh"
+
   - block: "Build CPU release image"
     key: block-cpu-release-image-build
     depends_on: ~
@@ -192,7 +250,7 @@ steps:
       - create-multi-arch-manifest
     if: build.env("NIGHTLY") == "1"
     agents:
-      queue: cpu_queue_postmerge
+      queue: small_cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
       - "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64"

.buildkite/scripts/upload-release-wheels.sh

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+
+set -e
+
+BUCKET="vllm-wheels"
+SUBPATH=$BUILDKITE_COMMIT
+S3_COMMIT_PREFIX="s3://$BUCKET/$SUBPATH/"
+
+RELEASE_VERSION=$(buildkite-agent meta-data get release-version)
+echo "Release version from Buildkite: $RELEASE_VERSION"
+GIT_VERSION=$(git describe --exact-match --tags $BUILDKITE_COMMIT 2>/dev/null)
+if [ -z "$GIT_VERSION" ]; then
+    echo "[FATAL] Not on a git tag, cannot create release."
+    exit 1
+else
+    echo "Git version for commit $BUILDKITE_COMMIT: $GIT_VERSION"
+fi
+# sanity check for version mismatch
+if [ "v$RELEASE_VERSION" != "$GIT_VERSION" ]; then
+  if [ "$FORCE_RELEASE_IGNORE_VERSION_MISMATCH" == "true" ]; then
+    echo "[WARNING] Force release and ignore version mismatch"
+  else
+    echo "[FATAL] Release version from Buildkite does not match Git version."
+    exit 1
+  fi
+fi
+
+# check pypi token
+if [ -z "$PYPI_TOKEN" ]; then
+  echo "[FATAL] PYPI_TOKEN is not set."
+  exit 1
+else
+  export TWINE_USERNAME="__token__"
+  export TWINE_PASSWORD="$PYPI_TOKEN"
+fi
+
+# check github token
+if [ -z "$GITHUB_TOKEN" ]; then
+  echo "[FATAL] GITHUB_TOKEN is not set."
+  exit 1
+else
+  export GH_TOKEN="$GITHUB_TOKEN"
+fi
+
+set -x # avoid printing secrets above
+
+# download gh CLI from github
+# Get latest gh CLI version from GitHub API
+GH_VERSION=$(curl -s https://api.github.com/repos/cli/cli/releases/latest | grep '"tag_name":' | sed -E 's/.*"([^"]+)".*/\1/' | sed 's/^v//')
+if [ -z "$GH_VERSION" ]; then
+  echo "[FATAL] Failed to get latest gh CLI version from GitHub"
+  exit 1
+fi
+echo "Downloading gh CLI version: $GH_VERSION"
+GH_TARBALL="gh_${GH_VERSION}_linux_amd64.tar.gz"
+GH_URL="https://github.com/cli/cli/releases/download/v${GH_VERSION}/${GH_TARBALL}"
+GH_INSTALL_DIR="/tmp/gh-install"
+mkdir -p "$GH_INSTALL_DIR"
+pushd "$GH_INSTALL_DIR"
+curl -L -o "$GH_TARBALL" "$GH_URL"
+tar -xzf "$GH_TARBALL"
+GH_BIN=$(realpath $(find . -name "gh" -type f -executable | head -n 1))
+if [ -z "$GH_BIN" ]; then
+  echo "[FATAL] Failed to find gh CLI executable"
+  exit 1
+fi
+echo "gh CLI downloaded successfully, version: $($GH_BIN --version)"
+echo "Last 5 releases on GitHub:" # as a sanity check of gh and GH_TOKEN
+command "$GH_BIN" release list --limit 5
+popd
+
+# install twine from pypi
+python3 -m venv /tmp/vllm-release-env
+source /tmp/vllm-release-env/bin/activate
+pip install twine
+python3 -m twine --version
+
+# copy release wheels to local directory
+DIST_DIR=/tmp/vllm-release-dist
+echo "Existing wheels on S3:"
+aws s3 ls "$S3_COMMIT_PREFIX"
+echo "Copying wheels to local directory"
+mkdir -p $DIST_DIR
+# include only wheels for the release version, ignore all files with "dev" or "rc" in the name
+aws s3 cp --recursive --exclude "*" --include "vllm-${RELEASE_VERSION}*.whl" --exclude "*dev*" --exclude "*rc*" "$S3_COMMIT_PREFIX" $DIST_DIR
+echo "Wheels copied to local directory"
+# generate source tarball
+git archive --format=tar.gz --output="$DIST_DIR/vllm-${RELEASE_VERSION}.tar.gz" $BUILDKITE_COMMIT
+ls -la $DIST_DIR
+
+
+# upload wheels to PyPI (only default variant, i.e. files without '+' in the name)
+PYPI_WHEEL_FILES=$(find $DIST_DIR -name "vllm-${RELEASE_VERSION}*.whl" -not -name "*+*")
+if [ -z "$PYPI_WHEEL_FILES" ]; then
+  echo "No default variant wheels found, quitting..."
+  exit 1
+fi
+python3 -m twine check $PYPI_WHEEL_FILES
+python3 -m twine --non-interactive --verbose upload $PYPI_WHEEL_FILES
+echo "Wheels uploaded to PyPI"
+
+# create release on GitHub with the release version and all wheels
+command "$GH_BIN" release create $GIT_VERSION -d --latest --notes-from-tag --verify-tag $DIST_DIR/*.whl

docker/Dockerfile.rocm

@@ -85,6 +85,8 @@ ONBUILD COPY ./ vllm/
 FROM base AS fetch_vllm_1
 ARG VLLM_REPO="https://github.com/vllm-project/vllm.git"
 ARG VLLM_BRANCH="main"
+ENV VLLM_REPO=${VLLM_REPO}
+ENV VLLM_BRANCH=${VLLM_BRANCH}
 ONBUILD RUN git clone ${VLLM_REPO} \
 	    && cd vllm \
 	    && git fetch -v --prune -- origin ${VLLM_BRANCH} \
@@ -301,6 +303,10 @@ RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
     && pip uninstall -y vllm \
     && uv pip install --system *.whl
 
+# Install RIXL wheel
+RUN --mount=type=bind,from=build_rixl,src=/app/install,target=/rixl_install \
+    uv pip install --system /rixl_install/*.whl
+
 WORKDIR /vllm-workspace
 ARG COMMON_WORKDIR
 COPY --from=build_vllm ${COMMON_WORKDIR}/vllm /vllm-workspace

docker/Dockerfile.rocm_base

@@ -198,92 +198,6 @@ RUN cd mori \
 RUN mkdir -p /app/install && cp /app/mori/dist/*.whl /app/install
 
 
-###
-### RIXL Build
-###
-FROM build_pytorch AS build_rixl
-ARG RIXL_BRANCH
-ARG RIXL_REPO
-ARG ETCD_BRANCH
-ARG ETCD_REPO
-ARG UCX_BRANCH
-ARG UCX_REPO
-
-ENV ROCM_PATH=/opt/rocm
-ENV UCX_HOME=/usr/local/ucx
-ENV RIXL_HOME=/usr/local/rixl
-ENV RIXL_BENCH_HOME=/usr/local/rixl_bench
-
-# RIXL build system dependences and RDMA support
-RUN apt-get -y update && apt-get -y install autoconf libtool pkg-config \
-    libgrpc-dev \
-    libgrpc++-dev \
-    libprotobuf-dev \
-    protobuf-compiler-grpc \
-    libcpprest-dev \
-    libaio-dev \
-    librdmacm1 \
-    librdmacm-dev \
-    libibverbs1 \
-    libibverbs-dev \
-    ibverbs-utils \
-    rdmacm-utils \
-    ibverbs-providers
-
-RUN pip install meson auditwheel patchelf tomlkit
-
-WORKDIR /workspace
-
-RUN git clone ${ETCD_REPO} && \
-    cd etcd-cpp-apiv3 && \
-    git checkout ${ETCD_BRANCH} && \
-    mkdir build && cd build && \
-    cmake .. -DCMAKE_POLICY_VERSION_MINIMUM=3.5 && \
-    make -j$(nproc) && \
-    make install
-
-RUN cd /usr/local/src && \
-    git clone ${UCX_REPO} &&  \
-    cd ucx  && \
-    git checkout ${UCX_BRANCH} && \
-    ./autogen.sh && \
-    mkdir build && cd build && \
-    ../configure \
-        --prefix=/usr/local/ucx \
-        --enable-shared \
-        --disable-static \
-        --disable-doxygen-doc \
-        --enable-optimizations \
-        --enable-devel-headers \
-        --with-rocm=/opt/rocm \
-        --with-verbs \
-        --with-dm \
-        --enable-mt && \
-    make -j && \
-    make -j install
-
-ENV PATH=/usr/local/ucx/bin:$PATH
-ENV LD_LIBRARY_PATH=${UCX_HOME}/lib:${LD_LIBRARY_PATH}
-
-RUN git clone ${RIXL_REPO} /opt/rixl && \
-    cd /opt/rixl && \
-    git checkout ${RIXL_BRANCH} && \
-    meson setup build --prefix=${RIXL_HOME} \
-                     -Ducx_path=${UCX_HOME} \
-                     -Drocm_path=${ROCM_PATH} && \
-    cd build && \
-    ninja && \
-    ninja install
-
-# Generate RIXL wheel
-RUN cd /opt/rixl && mkdir -p /app/install && \
-    ./contrib/build-wheel.sh \
-        --output-dir /app/install \
-        --rocm-dir ${ROCM_PATH} \
-        --ucx-plugins-dir ${UCX_HOME}/lib/ucx \
-        --nixl-plugins-dir ${RIXL_HOME}/lib/x86_64-linux-gnu/plugins
-
-
 ###
 ### FlashAttention Build
 ###
@@ -365,8 +279,6 @@ RUN --mount=type=bind,from=build_aiter,src=/app/install/,target=/install \
     cp /install/*.whl /app/debs
 RUN --mount=type=bind,from=build_mori,src=/app/install/,target=/install \
     cp /install/*.whl /app/debs
-RUN --mount=type=bind,from=build_rixl,src=/app/install/,target=/install \
-    cp /install/*.whl /app/debs
 
 FROM base AS final
 RUN --mount=type=bind,from=debs,src=/app/debs,target=/install \
@@ -385,12 +297,6 @@ ARG FA_BRANCH
 ARG FA_REPO
 ARG AITER_BRANCH
 ARG AITER_REPO
-ARG RIXL_BRANCH
-ARG RIXL_REPO
-ARG ETCD_BRANCH
-ARG ETCD_REPO
-ARG UCX_BRANCH
-ARG UCX_REPO
 ARG MORI_BRANCH
 ARG MORI_REPO
 RUN echo "BASE_IMAGE: ${BASE_IMAGE}" > /app/versions.txt \
@@ -406,11 +312,5 @@ RUN echo "BASE_IMAGE: ${BASE_IMAGE}" > /app/versions.txt \
     && echo "FA_REPO: ${FA_REPO}" >> /app/versions.txt \
     && echo "AITER_BRANCH: ${AITER_BRANCH}" >> /app/versions.txt \
     && echo "AITER_REPO: ${AITER_REPO}" >> /app/versions.txt \
-    && echo "RIXL_BRANCH: ${RIXL_BRANCH}" >> /app/versions.txt \
-    && echo "RIXL_REPO: ${RIXL_REPO}" >> /app/versions.txt \
-    && echo "ETCD_BRANCH: ${ETCD_BRANCH}" >> /app/versions.txt \
-    && echo "ETCD_REPO: ${ETCD_REPO}" >> /app/versions.txt \
-    && echo "UCX_BRANCH: ${UCX_BRANCH}" >> /app/versions.txt \
-    && echo "UCX_REPO: ${UCX_REPO}" >> /app/versions.txt \
     && echo "MORI_BRANCH: ${MORI_BRANCH}" >> /app/versions.txt \
     && echo "MORI_REPO: ${MORI_REPO}" >> /app/versions.txt

vllm/entrypoints/openai/api_server.py

@@ -540,14 +540,8 @@ async def create_completion(request: CompletionRequest, raw_request: Request):
 
     try:
         generator = await handler.create_completion(request, raw_request)
-    except OverflowError as e:
-        raise HTTPException(
-            status_code=HTTPStatus.BAD_REQUEST.value, detail=str(e)
-        ) from e
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
-        ) from e
 
     if isinstance(generator, ErrorResponse):
         return JSONResponse(

vllm/entrypoints/openai/serving_engine.py

@@ -86,7 +86,7 @@ from vllm.entrypoints.responses_utils import (
     construct_input_messages,
 )
 from vllm.entrypoints.serve.disagg.protocol import GenerateRequest, GenerateResponse
-from vllm.entrypoints.utils import _validate_truncation_size
+from vllm.entrypoints.utils import _validate_truncation_size, sanitize_message
 from vllm.inputs.data import PromptType, TokensPrompt
 from vllm.inputs.parse import (
     PromptComponents,
@@ -760,11 +760,15 @@ class OpenAIServing:
                 err_type = "BadRequestError"
                 status_code = HTTPStatus.BAD_REQUEST
                 param = exc.parameter
-            elif isinstance(exc, (ValueError, TypeError, RuntimeError)):
+            elif isinstance(exc, (ValueError, TypeError, RuntimeError, OverflowError)):
                 # Common validation errors from user input
                 err_type = "BadRequestError"
                 status_code = HTTPStatus.BAD_REQUEST
                 param = None
+            elif isinstance(exc, NotImplementedError):
+                err_type = "NotImplementedError"
+                status_code = HTTPStatus.NOT_IMPLEMENTED
+                param = None
             elif exc.__class__.__name__ == "TemplateError":
                 # jinja2.TemplateError (avoid importing jinja2)
                 err_type = "BadRequestError"
@@ -783,9 +787,10 @@ class OpenAIServing:
                 traceback.print_exc()
             else:
                 traceback.print_stack()
+
         return ErrorResponse(
             error=ErrorInfo(
-                message=message,
+                message=sanitize_message(message),
                 type=err_type,
                 code=status_code.value,
                 param=param,

vllm/entrypoints/openai/serving_models.py

@@ -16,6 +16,7 @@ from vllm.entrypoints.openai.protocol import (
     ModelPermission,
     UnloadLoRAAdapterRequest,
 )
+from vllm.entrypoints.utils import sanitize_message
 from vllm.logger import init_logger
 from vllm.lora.request import LoRARequest
 from vllm.lora.resolver import LoRAResolver, LoRAResolverRegistry
@@ -300,5 +301,9 @@ def create_error_response(
     status_code: HTTPStatus = HTTPStatus.BAD_REQUEST,
 ) -> ErrorResponse:
     return ErrorResponse(
-        error=ErrorInfo(message=message, type=err_type, code=status_code.value)
+        error=ErrorInfo(
+            message=sanitize_message(message),
+            type=err_type,
+            code=status_code.value,
+        )
     )

vllm/entrypoints/pooling/classify/api_router.py

@@ -1,8 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-from http import HTTPStatus
 
-from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi import APIRouter, Depends, Request
 from starlette.responses import JSONResponse
 from typing_extensions import assert_never
 
@@ -36,9 +35,8 @@ async def create_classify(request: ClassificationRequest, raw_request: Request):
     try:
         generator = await handler.create_classify(request, raw_request)
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
+
-        ) from e
     if isinstance(generator, ErrorResponse):
         return JSONResponse(
             content=generator.model_dump(), status_code=generator.error.code

vllm/entrypoints/pooling/embed/api_router.py

@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from http import HTTPStatus
 
-from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi import APIRouter, Depends, Request
 from fastapi.responses import JSONResponse, StreamingResponse
 from typing_extensions import assert_never
 
@@ -47,9 +47,7 @@ async def create_embedding(
     try:
         generator = await handler.create_embedding(request, raw_request)
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
-        ) from e
 
     if isinstance(generator, ErrorResponse):
         return JSONResponse(

vllm/entrypoints/pooling/pooling/api_router.py

@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from http import HTTPStatus
 
-from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi import APIRouter, Depends, Request
 from fastapi.responses import JSONResponse, StreamingResponse
 from typing_extensions import assert_never
 
@@ -44,9 +44,8 @@ async def create_pooling(request: PoolingRequest, raw_request: Request):
     try:
         generator = await handler.create_pooling(request, raw_request)
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
+
-        ) from e
     if isinstance(generator, ErrorResponse):
         return JSONResponse(
             content=generator.model_dump(), status_code=generator.error.code

vllm/entrypoints/pooling/score/api_router.py

@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from http import HTTPStatus
 
-from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi import APIRouter, Depends, Request
 from fastapi.responses import JSONResponse
 from typing_extensions import assert_never
 
@@ -52,9 +52,8 @@ async def create_score(request: ScoreRequest, raw_request: Request):
     try:
         generator = await handler.create_score(request, raw_request)
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
+
-        ) from e
     if isinstance(generator, ErrorResponse):
         return JSONResponse(
             content=generator.model_dump(), status_code=generator.error.code
@@ -104,9 +103,8 @@ async def do_rerank(request: RerankRequest, raw_request: Request):
     try:
         generator = await handler.do_rerank(request, raw_request)
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
+
-        ) from e
     if isinstance(generator, ErrorResponse):
         return JSONResponse(
             content=generator.model_dump(), status_code=generator.error.code

vllm/entrypoints/serve/disagg/api_router.py

@@ -67,9 +67,8 @@ async def generate(request: GenerateRequest, raw_request: Request):
     try:
         generator = await handler.serve_tokens(request, raw_request)
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
+
-        ) from e
     if isinstance(generator, ErrorResponse):
         return JSONResponse(
             content=generator.model_dump(), status_code=generator.error.code

vllm/entrypoints/serve/tokenize/api_router.py

@@ -49,14 +49,8 @@ async def tokenize(request: TokenizeRequest, raw_request: Request):
 
     try:
         generator = await handler.create_tokenize(request, raw_request)
-    except NotImplementedError as e:
-        raise HTTPException(
-            status_code=HTTPStatus.NOT_IMPLEMENTED.value, detail=str(e)
-        ) from e
     except Exception as e:
-        raise HTTPException(
+        return handler.create_error_response(e)
-            status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
-        ) from e
 
     if isinstance(generator, ErrorResponse):
         return JSONResponse(

vllm/entrypoints/utils.py

@@ -7,7 +7,7 @@ import functools
 import os
 from argparse import Namespace
 from pathlib import Path
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 import regex as re
 from fastapi import Request
@@ -22,18 +22,25 @@ from vllm.entrypoints.chat_utils import (
     resolve_hf_chat_template,
     resolve_mistral_chat_template,
 )
-from vllm.entrypoints.openai.cli_args import make_arg_parser
-from vllm.entrypoints.openai.protocol import (
-    ChatCompletionRequest,
-    CompletionRequest,
-    StreamOptions,
-)
-from vllm.entrypoints.openai.serving_models import LoRAModulePath
 from vllm.logger import init_logger
 from vllm.platforms import current_platform
 from vllm.tokenizers.mistral import MistralTokenizer
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 
+if TYPE_CHECKING:
+    from vllm.entrypoints.openai.protocol import (
+        ChatCompletionRequest,
+        CompletionRequest,
+        StreamOptions,
+    )
+    from vllm.entrypoints.openai.serving_models import LoRAModulePath
+else:
+    ChatCompletionRequest = object
+    CompletionRequest = object
+    StreamOptions = object
+    LoRAModulePath = object
+
+
 logger = init_logger(__name__)
 
 VLLM_SUBCMD_PARSER_EPILOG = (
@@ -206,7 +213,7 @@ def _validate_truncation_size(
 
 def get_max_tokens(
     max_model_len: int,
-    request: ChatCompletionRequest | CompletionRequest,
+    request: "ChatCompletionRequest | CompletionRequest",
     input_length: int,
     default_sampling_params: dict,
 ) -> int:
@@ -227,6 +234,8 @@ def get_max_tokens(
 
 
 def log_non_default_args(args: Namespace | EngineArgs):
+    from vllm.entrypoints.openai.cli_args import make_arg_parser
+
     non_default_args = {}
 
     # Handle Namespace
@@ -255,7 +264,7 @@ def log_non_default_args(args: Namespace | EngineArgs):
 
 
 def should_include_usage(
-    stream_options: StreamOptions | None, enable_force_include_usage: bool
+    stream_options: "StreamOptions | None", enable_force_include_usage: bool
 ) -> tuple[bool, bool]:
     if stream_options:
         include_usage = stream_options.include_usage or enable_force_include_usage
@@ -270,6 +279,8 @@ def should_include_usage(
 def process_lora_modules(
     args_lora_modules: list[LoRAModulePath], default_mm_loras: dict[str, str] | None
 ) -> list[LoRAModulePath]:
+    from vllm.entrypoints.openai.serving_models import LoRAModulePath
+
     lora_modules = args_lora_modules
     if default_mm_loras:
         default_mm_lora_paths = [