[CI] fix version comparsion and exclusion patterns in upload-release-wheels.sh (#32971)

Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
(cherry picked from commit 136c499f6e)

.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 +109,93 @@ 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=13.0.1 --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-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"
+      # compute capability 12.0 for RTX-50 series / RTX PRO 6000 Blackwell, 12.1 for DGX Spark
+      - "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 12.1' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-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: ~
@@ -186,25 +245,14 @@ steps:
       - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg BASE_IMAGE=rocm/vllm-dev:base-$BUILDKITE_COMMIT --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-rocm --target vllm-openai --progress plain -f docker/Dockerfile.rocm ."
       - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-rocm"
   
-  
   - label: "Build and publish nightly multi-arch image to DockerHub"
     depends_on:
       - 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"
+      - "bash .buildkite/scripts/push-nightly-builds.sh"
-      - "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64"
-      - "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64"
-      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 vllm/vllm-openai:nightly-x86_64"
-      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 vllm/vllm-openai:nightly-aarch64"
-      - "docker push vllm/vllm-openai:nightly-x86_64"
-      - "docker push vllm/vllm-openai:nightly-aarch64"
-      - "docker manifest create vllm/vllm-openai:nightly vllm/vllm-openai:nightly-x86_64 vllm/vllm-openai:nightly-aarch64 --amend"
-      - "docker manifest create vllm/vllm-openai:nightly-$BUILDKITE_COMMIT vllm/vllm-openai:nightly-x86_64 vllm/vllm-openai:nightly-aarch64 --amend"
-      - "docker manifest push vllm/vllm-openai:nightly"
-      - "docker manifest push vllm/vllm-openai:nightly-$BUILDKITE_COMMIT"
       # Clean up old nightly builds (keep only last 14)
       - "bash .buildkite/scripts/cleanup-nightly-builds.sh"
     plugins:
@@ -215,6 +263,25 @@ steps:
       DOCKER_BUILDKIT: "1"
       DOCKERHUB_USERNAME: "vllmbot"
 
+  - label: "Build and publish nightly multi-arch image to DockerHub - CUDA 13.0"
+    depends_on:
+      - create-multi-arch-manifest-cuda-13-0
+    if: build.env("NIGHTLY") == "1"
+    agents:
+      queue: small_cpu_queue_postmerge
+    commands:
+      - "bash .buildkite/scripts/push-nightly-builds.sh cu130"
+      # Clean up old nightly builds (keep only last 14)
+      - "bash .buildkite/scripts/cleanup-nightly-builds.sh cu130-nightly-"
+    plugins:
+      - docker-login#v3.0.0:
+          username: vllmbot
+          password-env: DOCKERHUB_TOKEN
+    env:
+      DOCKER_BUILDKIT: "1"
+      DOCKERHUB_USERNAME: "vllmbot"
+
+
   # =============================================================================
   # ROCm Release Pipeline (x86_64 only)
   # =============================================================================

.buildkite/scripts/cleanup-nightly-builds.sh

@@ -3,7 +3,14 @@
 set -ex
 
 # Clean up old nightly builds from DockerHub, keeping only the last 14 builds
-# This script uses DockerHub API to list and delete old tags with "nightly-" prefix
+# This script uses DockerHub API to list and delete old tags with specified prefix
+# Usage: cleanup-nightly-builds.sh [TAG_PREFIX]
+# Example: cleanup-nightly-builds.sh "nightly-" or cleanup-nightly-builds.sh "cu130-nightly-"
+
+# Get tag prefix from argument, default to "nightly-" if not provided
+TAG_PREFIX="${1:-nightly-}"
+
+echo "Cleaning up tags with prefix: $TAG_PREFIX"
 
 # DockerHub API endpoint for vllm/vllm-openai repository
 REPO_API_URL="https://hub.docker.com/v2/repositories/vllm/vllm-openai/tags"
@@ -45,7 +52,7 @@ get_all_tags() {
         set -x
         
         # Get both last_updated timestamp and tag name, separated by |
-        local tags=$(echo "$response" | jq -r '.results[] | select(.name | startswith("nightly-")) | "\(.last_updated)|\(.name)"')
+        local tags=$(echo "$response" | jq -r --arg prefix "$TAG_PREFIX" '.results[] | select(.name | startswith($prefix)) | "\(.last_updated)|\(.name)"')
         
         if [ -z "$tags" ]; then
             break

.buildkite/scripts/push-nightly-builds.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+set -ex
+
+# Get tag variant from argument, default to empty if not provided, should be something like "cu130".
+# Due to limits in cleanup script, we must move variants to use separate tags like "cu130-nightly",
+# otherwise they will be cleaned up together with the main "nightly" tags.
+
+TAG_VARIANT="$1"
+if [ -n "$TAG_VARIANT" ]; then
+    ORIG_TAG_SUFFIX="-$TAG_VARIANT"
+    TAG_NAME="$TAG_VARIANT-nightly"
+else
+    ORIG_TAG_SUFFIX=""
+    TAG_NAME="nightly"
+fi
+
+ORIG_TAG_NAME="$BUILDKITE_COMMIT"
+
+echo "Pushing original tag $ORIG_TAG_NAME$ORIG_TAG_SUFFIX to new nightly tag name: $TAG_NAME"
+
+# pull original arch-dependent images from AWS ECR Public
+aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
+docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-x86_64$ORIG_TAG_SUFFIX
+docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-aarch64$ORIG_TAG_SUFFIX
+# tag arch-dependent images
+docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-x86_64$ORIG_TAG_SUFFIX vllm/vllm-openai:$TAG_NAME-x86_64
+docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-aarch64$ORIG_TAG_SUFFIX vllm/vllm-openai:$TAG_NAME-aarch64
+# push arch-dependent images to DockerHub
+docker push vllm/vllm-openai:$TAG_NAME-x86_64
+docker push vllm/vllm-openai:$TAG_NAME-aarch64
+# push arch-independent manifest to DockerHub
+docker manifest create vllm/vllm-openai:$TAG_NAME vllm/vllm-openai:$TAG_NAME-x86_64 vllm/vllm-openai:$TAG_NAME-aarch64 --amend
+docker manifest create vllm/vllm-openai:$TAG_NAME-$BUILDKITE_COMMIT vllm/vllm-openai:$TAG_NAME-x86_64 vllm/vllm-openai:$TAG_NAME-aarch64 --amend
+docker manifest push vllm/vllm-openai:$TAG_NAME
+docker manifest push vllm/vllm-openai:$TAG_NAME-$BUILDKITE_COMMIT

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

@@ -0,0 +1,104 @@
+#!/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: $GIT_VERSION"
+fi
+# sanity check for version mismatch
+if [ "$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
+PURE_VERSION=${RELEASE_VERSION#v} # remove leading 'v'
+
+# check pypi token
+if [ -z "$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 $DIST_DIR
+# include only wheels for the release version, ignore all files with "dev" or "rc" in the name (without excluding 'aarch64')
+aws s3 cp --recursive --exclude "*" --include "vllm-${PURE_VERSION}*.whl" --exclude "*dev*" --exclude "*rc[0-9]*" "$S3_COMMIT_PREFIX" $DIST_DIR
+echo "Wheels copied to local directory"
+# generate source tarball
+git archive --format=tar.gz --output="$DIST_DIR/vllm-${PURE_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 $DIST_DIR -name "vllm-${PURE_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

requirements/common.txt

@@ -32,7 +32,7 @@ pyzmq >= 25.0.0
 msgspec
 gguf >= 0.17.0
 mistral_common[image] >= 1.8.8
-opencv-python-headless >= 4.11.0    # required for video IO
+opencv-python-headless >= 4.13.0    # required for video IO
 pyyaml
 six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
 setuptools>=77.0.3,<81.0.0; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12

requirements/nightly_torch_test.txt

@@ -25,7 +25,7 @@ transformers_stream_generator # required for qwen-vl test
 matplotlib # required for qwen-vl test
 mistral_common[image,audio] >= 1.8.8 # required for voxtral test
 num2words # required for smolvlm test
-opencv-python-headless >= 4.11.0 # required for video test
+opencv-python-headless >= 4.13.0 # required for video test
 datamodel_code_generator # required for minicpm3 test
 lm-eval[api]>=0.4.9.2 # required for model evaluation test
 mteb>=1.38.11, <2 # required for mteb test
@@ -37,8 +37,8 @@ bitsandbytes>=0.46.1
 buildkite-test-collector==0.1.9
 
 
-genai_perf==0.0.8
+genai_perf>=0.0.8
-tritonclient==2.51.0
+tritonclient>=2.51.0
 
 numba == 0.61.2 # Required for N-gram speculative decoding
 numpy

requirements/test.in

@@ -33,7 +33,7 @@ matplotlib # required for qwen-vl test
 mistral_common[image,audio] >= 1.8.8 # required for voxtral test
 num2words # required for smolvlm test
 open_clip_torch==2.32.0 # Required for nemotron_vl test, Nemotron Parse in test_common.py
-opencv-python-headless >= 4.11.0 # required for video test
+opencv-python-headless >= 4.13.0 # required for video test
 datamodel_code_generator # required for minicpm3 test
 lm-eval[api]>=0.4.9.2 # required for model evaluation test
 mteb[bm25s]>=2, <3 # required for mteb test
@@ -45,8 +45,8 @@ bitsandbytes==0.46.1
 buildkite-test-collector==0.1.9
 
 
-genai_perf==0.0.8
+genai_perf>=0.0.8
-tritonclient==2.51.0
+tritonclient>=2.51.0
 
 arctic-inference == 0.1.1 # Required for suffix decoding test
 numba == 0.61.2 # Required for N-gram speculative decoding

requirements/test.txt

@@ -31,7 +31,11 @@ albumentations==1.4.6
     #   -r requirements/test.in
     #   terratorch
 alembic==1.16.4
-    # via mlflow
+    # via
+    #   mlflow
+    #   optuna
+annotated-doc==0.0.4
+    # via fastapi
 annotated-types==0.7.0
     # via pydantic
 antlr4-python3-runtime==4.9.3
@@ -143,6 +147,8 @@ colorama==0.4.6
     #   tqdm-multiprocess
 colorful==0.5.6
     # via ray
+colorlog==6.10.1
+    # via optuna
 contourpy==1.3.0
     # via matplotlib
 coverage==7.10.6
@@ -250,7 +256,7 @@ fsspec==2024.9.0
     #   torch
 ftfy==6.3.1
     # via open-clip-torch
-genai-perf==0.0.8
+genai-perf==0.0.16
     # via -r requirements/test.in
 genson==1.3.0
     # via datamodel-code-generator
@@ -387,6 +393,7 @@ jinja2==3.1.6
     # via
     #   datamodel-code-generator
     #   flask
+    #   genai-perf
     #   mlflow
     #   torch
 jiwer==3.0.5
@@ -526,7 +533,7 @@ numba==0.61.2
     #   librosa
 numexpr==2.10.1
     # via lm-eval
-numpy==1.26.4
+numpy==2.2.6
     # via
     #   -r requirements/test.in
     #   accelerate
@@ -556,6 +563,7 @@ numpy==1.26.4
     #   numba
     #   numexpr
     #   opencv-python-headless
+    #   optuna
     #   pandas
     #   patsy
     #   peft
@@ -635,7 +643,7 @@ opencensus==0.11.4
     # via ray
 opencensus-context==0.1.3
     # via opencensus
-opencv-python-headless==4.11.0.86
+opencv-python-headless==4.13.0.90
     # via
     #   -r requirements/test.in
     #   albucore
@@ -658,6 +666,10 @@ opentelemetry-sdk==1.35.0
     #   ray
 opentelemetry-semantic-conventions==0.56b0
     # via opentelemetry-sdk
+optuna==3.6.1
+    # via genai-perf
+orjson==3.11.5
+    # via genai-perf
 packaging==24.2
     # via
     #   accelerate
@@ -676,6 +688,7 @@ packaging==24.2
     #   lightning-utilities
     #   matplotlib
     #   mlflow-skinny
+    #   optuna
     #   peft
     #   plotly
     #   pooch
@@ -715,6 +728,8 @@ peft==0.16.0
     #   lm-eval
 perceptron==0.1.4
     # via -r requirements/test.in
+perf-analyzer==0.1.0
+    # via genai-perf
 pillow==10.4.0
     # via
     #   genai-perf
@@ -901,6 +916,7 @@ pyyaml==6.0.2
     #   lightning
     #   mlflow-skinny
     #   omegaconf
+    #   optuna
     #   peft
     #   pytorch-lightning
     #   ray
@@ -1063,6 +1079,7 @@ sortedcontainers==2.4.0
 soundfile==0.12.1
     # via
     #   -r requirements/test.in
+    #   genai-perf
     #   librosa
     #   mistral-common
 soxr==0.5.0.post1
@@ -1073,6 +1090,7 @@ sqlalchemy==2.0.41
     # via
     #   alembic
     #   mlflow
+    #   optuna
 sqlitedict==2.1.0
     # via lm-eval
 sqlparse==0.5.3
@@ -1202,6 +1220,7 @@ tqdm==4.66.6
     #   mteb
     #   nltk
     #   open-clip-torch
+    #   optuna
     #   peft
     #   pqdm
     #   pretrainedmodels
@@ -1224,10 +1243,8 @@ transformers-stream-generator==0.0.5
     # via -r requirements/test.in
 triton==3.5.1
     # via torch
-tritonclient==2.51.0
+tritonclient==2.64.0
-    # via
+    # via -r requirements/test.in
-    #   -r requirements/test.in
-    #   genai-perf
 typepy==1.3.2
     # via
     #   dataproperty

tests/entrypoints/openai/test_translation_validation.py

@@ -267,12 +267,16 @@ async def test_audio_with_max_tokens(mary_had_lamb, client_and_model):
     out_tokens = tok(out_text, add_special_tokens=False)["input_ids"]
     assert len(out_tokens) == 1
     # max_completion_tokens > max_model_len
+    # max_model_len=32768 for Gemma-3n-E2B-it
     transcription = await client.audio.transcriptions.create(
         model=model_name,
         file=mary_had_lamb,
         response_format="text",
         temperature=0.0,
-        extra_body={"max_completion_tokens": int(1e6)},
+        extra_body={
+            "max_completion_tokens": int(1e6),
+            "repetition_penalty": 1.3,
+        },
     )
     out = json.loads(transcription)
     out_text = out["text"]

tests/models/multimodal/generation/test_whisper.py

@@ -176,3 +176,46 @@ def test_models_distributed(
         distributed_executor_backend=distributed_executor_backend,
         enforce_eager=False,
     )
+
+
+@pytest.mark.core_model
+@pytest.mark.parametrize("model", ["openai/whisper-large-v3-turbo"])
+def test_encoder_cache_cleanup(
+    vllm_runner,
+    model: str,
+    input_audios,
+    monkeypatch,
+) -> None:
+    """Test that encoder cache is properly cleaned up after requests complete.
+
+    This is a regression test for a bug where encoder cache entries were freed
+    in the same scheduling step they were allocated, before the model could use
+    them.
+    """
+    # Set single-process mode to access the model runner's encoder cache directly
+    monkeypatch.setenv("VLLM_ENABLE_V1_MULTIPROCESSING", "0")
+    check_model_available(model)
+
+    with vllm_runner(
+        model,
+        dtype="half",
+        max_model_len=448,
+        tensor_parallel_size=1,
+        limit_mm_per_prompt={"audio": 2},
+        enforce_eager=True,
+    ) as vllm_model:
+        engine_core = vllm_model.llm.llm_engine.engine_core.engine_core
+        model_runner = engine_core.model_executor.driver_worker.worker.model_runner
+        encoder_cache = model_runner.encoder_cache
+
+        # Run multiple sequential requests to ensure cache is properly managed
+        for vllm_prompts, _, audios in input_audios:
+            vllm_model.generate_greedy(vllm_prompts, max_tokens=50, audios=audios)
+
+        # After all requests complete, encoder cache should be empty
+        cache_size = len(encoder_cache)
+        assert cache_size == 0, (
+            f"Encoder cache should be empty after all requests complete, "
+            f"but has {cache_size} entries. This indicates encoder cache "
+            f"entries are not being properly freed."
+        )

vllm/connections.py

@@ -3,10 +3,10 @@
 
 from collections.abc import Mapping, MutableMapping
 from pathlib import Path
-from urllib.parse import urlparse
 
 import aiohttp
 import requests
+from urllib3.util import parse_url
 
 from vllm.version import __version__ as VLLM_VERSION
 
@@ -37,7 +37,7 @@ class HTTPConnection:
         return self._async_client
 
     def _validate_http_url(self, url: str):
-        parsed_url = urlparse(url)
+        parsed_url = parse_url(url)
 
         if parsed_url.scheme not in ("http", "https"):
             raise ValueError(

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 = [

vllm/envs.py

@@ -442,9 +442,9 @@ def get_vllm_port() -> int | None:
     try:
         return int(port)
     except ValueError as err:
-        from urllib.parse import urlparse
+        from urllib3.util import parse_url
 
-        parsed = urlparse(port)
+        parsed = parse_url(port)
         if parsed.scheme:
             raise ValueError(
                 f"VLLM_PORT '{port}' appears to be a URI. "

vllm/multimodal/utils.py

@@ -9,13 +9,13 @@ from concurrent.futures import ThreadPoolExecutor
 from itertools import groupby
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, TypeVar
-from urllib.parse import ParseResult, urlparse
 from urllib.request import url2pathname
 
 import numpy as np
 import numpy.typing as npt
 import torch
 from PIL import Image, UnidentifiedImageError
+from urllib3.util import Url, parse_url
 
 import vllm.envs as envs
 from vllm.connections import HTTPConnection, global_http_connection
@@ -101,11 +101,14 @@ class MediaConnector:
 
     def _load_data_url(
         self,
-        url_spec: ParseResult,
+        url_spec: Url,
         media_io: MediaIO[_M],
     ) -> _M:  # type: ignore[type-var]
-        data_spec, data = url_spec.path.split(",", 1)
+        url_spec_path = url_spec.path or ""
+        data_spec, data = url_spec_path.split(",", 1)
         media_type, data_type = data_spec.split(";", 1)
+        # media_type starts with a leading "/" (e.g., "/video/jpeg")
+        media_type = media_type.lstrip("/")
 
         if data_type != "base64":
             msg = "Only base64 data URLs are supported for now."
@@ -115,7 +118,7 @@ class MediaConnector:
 
     def _load_file_url(
         self,
-        url_spec: ParseResult,
+        url_spec: Url,
         media_io: MediaIO[_M],
     ) -> _M:  # type: ignore[type-var]
         allowed_local_media_path = self.allowed_local_media_path
@@ -124,7 +127,9 @@ class MediaConnector:
                 "Cannot load local files without `--allowed-local-media-path`."
             )
 
-        filepath = Path(url2pathname(url_spec.netloc + url_spec.path))
+        url_spec_path = url_spec.path or ""
+        url_spec_netloc = url_spec.netloc or ""
+        filepath = Path(url2pathname(url_spec_netloc + url_spec_path))
         if allowed_local_media_path not in filepath.resolve().parents:
             raise ValueError(
                 f"The file path {filepath} must be a subpath "
@@ -133,7 +138,7 @@ class MediaConnector:
 
         return media_io.load_file(filepath)
 
-    def _assert_url_in_allowed_media_domains(self, url_spec: ParseResult) -> None:
+    def _assert_url_in_allowed_media_domains(self, url_spec: Url) -> None:
         if (
             self.allowed_media_domains
             and url_spec.hostname not in self.allowed_media_domains
@@ -151,9 +156,9 @@ class MediaConnector:
         *,
         fetch_timeout: int | None = None,
     ) -> _M:  # type: ignore[type-var]
-        url_spec = urlparse(url)
+        url_spec = parse_url(url)
 
-        if url_spec.scheme.startswith("http"):
+        if url_spec.scheme and url_spec.scheme.startswith("http"):
             self._assert_url_in_allowed_media_domains(url_spec)
 
             connection = self.connection
@@ -181,10 +186,10 @@ class MediaConnector:
         *,
         fetch_timeout: int | None = None,
     ) -> _M:
-        url_spec = urlparse(url)
+        url_spec = parse_url(url)
         loop = asyncio.get_running_loop()
 
-        if url_spec.scheme.startswith("http"):
+        if url_spec.scheme and url_spec.scheme.startswith("http"):
             self._assert_url_in_allowed_media_domains(url_spec)
 
             connection = self.connection

vllm/utils/network_utils.py

@@ -11,12 +11,12 @@ from collections.abc import (
     Sequence,
 )
 from typing import Any
-from urllib.parse import urlparse
 from uuid import uuid4
 
 import psutil
 import zmq
 import zmq.asyncio
+from urllib3.util import parse_url
 
 import vllm.envs as envs
 from vllm.logger import init_logger
@@ -217,13 +217,15 @@ def find_process_using_port(port: int) -> psutil.Process | None:
 
 def split_zmq_path(path: str) -> tuple[str, str, str]:
     """Split a zmq path into its parts."""
-    parsed = urlparse(path)
+    parsed = parse_url(path)
     if not parsed.scheme:
         raise ValueError(f"Invalid zmq path: {path}")
 
     scheme = parsed.scheme
     host = parsed.hostname or ""
     port = str(parsed.port or "")
+    if host.startswith("[") and host.endswith("]"):
+        host = host[1:-1]  # Remove brackets for IPv6 address
 
     if scheme == "tcp" and not all((host, port)):
         # The host and port fields are required for tcp

vllm/v1/core/encoder_cache_manager.py

@@ -357,7 +357,8 @@ class EncoderDecoderCacheManager(EncoderCacheManager):
     def __init__(self, cache_size: int):
         self.cache_size = cache_size
         self.num_free_slots = cache_size
-        self.freed: list[str] = []
+        self.allocated: list[str] = []
+        self.to_free: list[str] = []
 
     def check_and_update_cache(self, request: Request, input_id: int) -> bool:
         return False
@@ -383,7 +384,7 @@ class EncoderDecoderCacheManager(EncoderCacheManager):
         self.num_free_slots -= num_encoder_embeds
 
         mm_hash = request.mm_features[input_id].identifier
-        self.freed.append(mm_hash)
+        self.allocated.append(mm_hash)
 
     def free(self, request: Request) -> None:
         for input_id in range(len(request.mm_features)):
@@ -393,9 +394,14 @@ class EncoderDecoderCacheManager(EncoderCacheManager):
         return set(range(len(request.mm_features)))
 
     def get_freed_mm_hashes(self) -> list[str]:
-        freed = self.freed
+        # As encoder cache is not used for enc-dec models, we can free the entries here
-        self.freed = []
+        # The actual free happens in the runner, *before* the model is executed.
-        return freed
+        # Therefore, `freeable` acts as a buffer to free the entries only after the
+        # model is executed, mimicking the state transition of `EncoderCacheManager`.
+        to_free = self.to_free
+        self.to_free = self.allocated
+        self.allocated = []
+        return to_free
 
     def free_encoder_input(self, request: Request, input_id: int) -> None:
         num_encoder_embeds = request.get_num_encoder_embeds(input_id)