├── README.md ├── generic.Dockerfile ├── cuda.Dockerfile ├── scripts ├── lib.sh └── build-vllm.sh ├── .github └── workflows │ └── build.yml └── LICENSE /README.md: -------------------------------------------------------------------------------- 1 | # vLLM inference runtime 2 | 3 | This repo contains implementations of the vLLM inference runtime. 4 | 5 | -------------------------------------------------------------------------------- /generic.Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:24.04 2 | 3 | COPY scripts/lib.sh lib.sh 4 | COPY scripts/build-vllm.sh build-vllm.sh 5 | RUN ./build-vllm.sh generic 6 | 7 | -------------------------------------------------------------------------------- /cuda.Dockerfile: -------------------------------------------------------------------------------- 1 | ARG CUDA_VERSION=12.9.0 2 | ARG CUDA_IMAGE_VARIANT=ubuntu24.04 3 | 4 | FROM nvidia/cuda:${CUDA_VERSION}-devel-${CUDA_IMAGE_VARIANT} 5 | 6 | COPY scripts/lib.sh lib.sh 7 | COPY scripts/build-vllm.sh build-vllm.sh 8 | RUN ./build-vllm.sh cuda 9 | 10 | -------------------------------------------------------------------------------- /scripts/lib.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | available() { 4 | command -v "$1" >/dev/null 5 | } 6 | 7 | is_rhel_based() { # doesn't include openEuler 8 | # shellcheck disable=SC1091 9 | source /etc/os-release 10 | [ "$ID" = "rhel" ] || [ "$ID" = "redhat" ] || [ "$ID" == "centos" ] 11 | } 12 | 13 | dnf_install_epel() { 14 | local rpm_exclude_list="selinux-policy,container-selinux" 15 | local url="https://dl.fedoraproject.org/pub/epel/epel-release-latest-9.noarch.rpm" 16 | dnf reinstall -y "$url" || dnf install -y "$url" --exclude "$rpm_exclude_list" 17 | crb enable # this is in epel-release, can only install epel-release via url 18 | } 19 | 20 | add_stream_repo() { 21 | local uname_m 22 | uname_m="$(uname -m)" 23 | local url="https://mirror.stream.centos.org/9-stream/$1/$uname_m/os/" 24 | dnf config-manager --add-repo "$url" 25 | url="http://mirror.centos.org/centos/RPM-GPG-KEY-CentOS-Official" 26 | local file="/etc/pki/rpm-gpg/RPM-GPG-KEY-CentOS-Official" 27 | if [ ! -e $file ]; then 28 | curl --retry 8 --retry-all-errors -o $file "$url" 29 | rpm --import $file 30 | fi 31 | } 32 | 33 | rm_non_ubi_repos() { 34 | local dir="/etc/yum.repos.d" 35 | rm -rf $dir/mirror.stream.centos.org_9-stream_* $dir/epel* 36 | } 37 | 38 | git_clone_specific_commit() { 39 | local repo="${1##*/}" 40 | git init "$repo" 41 | cd "$repo" || return 1 42 | git remote add origin "$1" 43 | git fetch --depth 1 origin "$2" 44 | git reset --hard "FETCH_HEAD" 45 | git submodule update --init --recursive 46 | } 47 | -------------------------------------------------------------------------------- /.github/workflows/build.yml: -------------------------------------------------------------------------------- 1 | name: Build vLLM 2 | run-name: Build vLLM 3 | 4 | on: 5 | push: 6 | branches: [ "main" ] 7 | pull_request: 8 | branches: [ "main" ] 9 | workflow_dispatch: 10 | inputs: 11 | release: 12 | description: 'Publish artifacts produced by this job' 13 | required: false 14 | type: boolean 15 | default: false 16 | pushLatest: 17 | description: 'Tag artifacts produced by this job as latest-*' 18 | required: false 19 | type: boolean 20 | default: false 21 | releaseTag: 22 | description: 'Release tag' 23 | required: false 24 | type: string 25 | 26 | jobs: 27 | build_native_linux_cpu: 28 | runs-on: ubuntu-latest 29 | steps: 30 | - name: Checkout repo 31 | uses: actions/checkout@v4 32 | with: 33 | submodules: 'true' 34 | 35 | - name: Login to DockerHub 36 | uses: docker/login-action@v3 37 | with: 38 | username: ${{ vars.DOCKERBUILDBOT_USERNAME }} 39 | password: ${{ secrets.DOCKERBUILDBOT_WRITE_PAT }} 40 | 41 | - name: Set up Docker Buildx 42 | uses: docker/setup-buildx-action@v3 43 | with: 44 | version: "lab:latest" 45 | driver: cloud 46 | endpoint: "docker/make-product-smarter" 47 | install: true 48 | 49 | - name: Build generic vLLM 50 | uses: docker/build-push-action@v5 51 | with: 52 | file: ${{ github.workspace }}generic.Dockerfile 53 | platforms: linux/amd64, linux/arm64 54 | context: ${{ github.workspace }} 55 | build-args: | 56 | "BASE_IMAGE="ubuntu:24.04" 57 | push: false 58 | sbom: true 59 | provenance: mode=max 60 | outputs: type=local,dest=${{ github.workspace }}/out 61 | 62 | build_native_linux_cuda: 63 | runs-on: ubuntu-latest 64 | steps: 65 | - name: Checkout repo 66 | uses: actions/checkout@v4 67 | with: 68 | submodules: 'true' 69 | 70 | - name: Login to DockerHub 71 | uses: docker/login-action@v3 72 | with: 73 | username: ${{ vars.DOCKERBUILDBOT_USERNAME }} 74 | password: ${{ secrets.DOCKERBUILDBOT_WRITE_PAT }} 75 | 76 | - name: Set up Docker Buildx 77 | uses: docker/setup-buildx-action@v3 78 | with: 79 | version: "lab:latest" 80 | driver: cloud 81 | endpoint: "docker/make-product-smarter" 82 | install: true 83 | 84 | - name: Build CUDA accelerated vLLM 85 | uses: docker/build-push-action@v5 86 | with: 87 | file: ${{ github.workspace }}/cuda.Dockerfile 88 | platforms: linux/amd64, linux/arm64 89 | context: ${{ github.workspace }}/native 90 | build-args: | 91 | "CUDA_VERSION=12.9.0" 92 | "CUDA_IMAGE_VARIANT=ubuntu24.04" 93 | push: false 94 | sbom: true 95 | provenance: mode=max 96 | outputs: type=local,dest=${{ github.workspace }}/out 97 | 98 | -------------------------------------------------------------------------------- /scripts/build-vllm.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | install_deps() { 4 | if available dnf; then 5 | dnf install -y git wget ca-certificates gcc gcc-c++ libSM libXext \ 6 | mesa-libGL jq lsof vim numactl 7 | if is_rhel_based; then 8 | add_stream_repo "AppStream" 9 | dnf install -y numactl-devel 10 | rm_non_ubi_repos 11 | 12 | dnf_install_epel 13 | dnf install -y gperftools-libs 14 | rm_non_ubi_repos 15 | else 16 | dnf install -y numactl-devel gperftools-libs 17 | fi 18 | 19 | dnf -y clean all 20 | rm -rf /var/cache/*dnf* 21 | elif available apt-get; then 22 | apt-get update -y 23 | apt-get install -y --no-install-recommends git curl wget ca-certificates \ 24 | gcc g++ libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 \ 25 | jq lsof vim numactl 26 | rm -rf /var/lib/apt/lists/* 27 | fi 28 | 29 | curl -LsSf https://astral.sh/uv/0.8.17/install.sh | bash 30 | } 31 | 32 | add_to_environment() { 33 | if grep -q "^$1=" /etc/environment; then 34 | echo "$1 already exists in /etc/environment" 35 | return 1 36 | fi 37 | 38 | echo "$1=$2" >> /etc/environment 39 | } 40 | 41 | preload_and_ulimit() { 42 | if [ "$containerfile" = "generic" ]; then 43 | local ld_preload_file="libtcmalloc_minimal.so.4" 44 | local ld_preload_file_1="/usr/lib/$uname_m-linux-gnu/$ld_preload_file" 45 | local ld_preload_file_2="/usr/lib64/$ld_preload_file" 46 | if [ -e "$ld_preload_file_1" ]; then 47 | ld_preload_file="$ld_preload_file_1" 48 | elif [ -e "$ld_preload_file_2" ]; then 49 | ld_preload_file="$ld_preload_file_2" 50 | fi 51 | 52 | if [ -e "$ld_preload_file" ]; then 53 | add_to_environment "LD_PRELOAD" "$ld_preload_file" 54 | fi 55 | fi 56 | 57 | echo 'ulimit -c 0' >> ~/.bashrc 58 | export PATH="/opt/app-root/bin:$virtual_env/bin:/root/.local/bin:$PATH" 59 | # add_to_environment "PATH" "$PATH" 60 | } 61 | 62 | pip_install() { 63 | local url="https://download.pytorch.org/whl" 64 | if [ "$containerfile" = "generic" ]; then 65 | url="$url/cpu" 66 | elif [ "$containerfile" = "cuda" ]; then 67 | url="$url/cu$(echo "$CUDA_VERSION" | cut -d. -f1,2 | tr -d '.')" 68 | fi 69 | 70 | export UV_HTTP_TIMEOUT="500" 71 | export UV_INDEX_STRATEGY="unsafe-best-match" 72 | uv pip install -v -r "$1" --extra-index-url "$url" 73 | } 74 | 75 | pip_install_all() { 76 | if [ "$containerfile" = "generic" ]; then 77 | pip_install requirements/cpu-build.txt 78 | pip_install requirements/cpu.txt 79 | elif [ "$containerfile" = "cuda" ]; then 80 | pip_install requirements/build.txt 81 | pip_install requirements/cuda.txt 82 | fi 83 | } 84 | 85 | set_vllm_env_vars() { 86 | if [ "$containerfile" = "generic" ]; then 87 | export VLLM_TARGET_DEVICE="cpu" 88 | if [ "$uname_m" == "x86_64" ]; then 89 | export VLLM_CPU_DISABLE_AVX512="0" 90 | export VLLM_CPU_AVX512BF16="0" 91 | export VLLM_CPU_AVX512VNNI="0" 92 | elif [ "$uname_m" == "aarch64" ]; then 93 | export VLLM_CPU_DISABLE_AVX512="true" 94 | fi 95 | elif [ "$containerfile" = "cuda" ]; then 96 | export VLLM_TARGET_DEVICE="cuda" 97 | fi 98 | } 99 | 100 | main() { 101 | set -eux -o pipefail 102 | 103 | # shellcheck disable=SC1091 104 | source lib.sh 105 | 106 | local containerfile=$1 107 | if [ "$containerfile" != "generic" ] && [ "$containerfile" != "cuda" ]; then 108 | echo "First argument must be 'generic' or 'cuda'. Got: '$containerfile'" 109 | return 1 110 | fi 111 | 112 | local uname_m 113 | uname_m=$(uname -m) 114 | 115 | install_deps 116 | local virtual_env="/opt/venv" 117 | preload_and_ulimit 118 | uv venv --python 3.11 --seed "$virtual_env" 119 | uv pip install --upgrade pip 120 | 121 | local vllm_url="https://github.com/vllm-project/vllm" 122 | local commit="26b999c71ab28ae9708329003007979530638f79" 123 | git_clone_specific_commit "$vllm_url" "$commit" 124 | set_vllm_env_vars 125 | pip_install_all 126 | 127 | # Have had to set MAX_JOBS as low as 1 while building, even on machine 128 | # with 32GB RAM, kept running out of memory causing crashes. 129 | MAX_JOBS=2 python3 setup.py install 130 | 131 | cd - 132 | rm -rf vllm /root/.cache 133 | } 134 | 135 | main "$@" 136 | 137 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------