feat(vllm): bundle libnuma/libgomp via package.sh

The vllm CPU wheel ships a _C extension that dlopens libnuma.so.1 at
import time; torch's CPU kernels in turn use libgomp.so.1 (OpenMP).
Without these on the host, vllm._C silently fails to register its
torch ops and EngineCore crashes with:

  AttributeError: '_OpNamespace' '_C_utils' object has no attribute
    'init_cpu_threads_env'

Rather than asking every user to install libnuma1/libgomp1 on their
host (or every LocalAI base image to ship them), bundle them into
the backend image itself — same pattern fish-speech and the GPU libs
already use. libbackend.sh adds ${EDIR}/lib to LD_LIBRARY_PATH at
run time so the bundled copies are picked up automatically.

- backend/python/vllm/package.sh (new): copies libnuma.so.1 and
  libgomp.so.1 from the builder's multilib paths into ${BACKEND}/lib,
  preserving soname symlinks. Runs during Dockerfile.python's
  'Run backend-specific packaging' step (which already invokes
  package.sh if present).
- backend/Dockerfile.python: install libnuma1 + libgomp1 in the
  builder stage so package.sh has something to copy (the Ubuntu
  base image otherwise only has libgomp in the gcc dep chain).
- test-extra.yml: drop the workaround that installed these libs on
  the runner host — with the backend image self-contained, the
  runner no longer needs them, and the test now exercises the
  packaging path end-to-end the way a production host would.
This commit is contained in:
Ettore Di Giacinto
2026-04-12 20:20:21 +00:00
parent 017bdee4e4
commit d74cd56b14
3 changed files with 57 additions and 6 deletions

View File

@@ -519,15 +519,16 @@ jobs:
- name: Dependencies
# bigger-runner is a bare self-hosted runner — install the tools
# we need for docker-build + protogen-go + go test (make, curl,
# unzip for the protoc download, build-essential for cgo), plus
# libnuma1 which the vllm CPU wheel's _C extension dlopens at
# runtime (libnuma.so.1 missing → init_cpu_threads_env op is not
# registered → AttributeError on LoadModel).
# unzip for the protoc download, build-essential for cgo).
# Runtime shared libraries the vllm backend needs (libnuma,
# libgomp) are packaged into the backend image via package.sh
# and NOT installed on the host — that way the CI exercises the
# packaging path end-to-end and catches missing libs that users
# would otherwise hit on a bare production host.
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
make build-essential curl unzip ca-certificates git tar \
libnuma1 libgomp1
make build-essential curl unzip ca-certificates git tar
- name: Setup Go
uses: actions/setup-go@v5
with:

View File

@@ -29,6 +29,7 @@ RUN apt-get update && \
curl python3-pip \
python-is-python3 \
python3-dev llvm \
libnuma1 libgomp1 \
python3-venv make cmake && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*

49
backend/python/vllm/package.sh Executable file
View File

@@ -0,0 +1,49 @@
#!/bin/bash
# Script to package runtime shared libraries for the vllm backend.
#
# The final Dockerfile.python stage is FROM scratch, so system libraries
# must be explicitly copied into ${BACKEND}/lib so the backend can run on
# any host without installing them. libbackend.sh automatically adds that
# directory to LD_LIBRARY_PATH at run time.
#
# vllm's CPU C++ extension (vllm._C) dlopens libnuma.so.1 at import time;
# if it's missing, the _C_utils torch ops are never registered and the
# engine crashes with AttributeError on init_cpu_threads_env. libgomp is
# used by torch's CPU kernels; on some stripped-down hosts it's also
# absent, so we bundle it too.
set -e
CURDIR=$(dirname "$(realpath "$0")")
LIB_DIR="${CURDIR}/lib"
mkdir -p "${LIB_DIR}"
copy_with_symlinks() {
local soname="$1"
local hit=""
for dir in /usr/lib/x86_64-linux-gnu /usr/lib/aarch64-linux-gnu /lib/x86_64-linux-gnu /lib/aarch64-linux-gnu /usr/lib /lib; do
if [ -e "${dir}/${soname}" ]; then
hit="${dir}/${soname}"
break
fi
done
if [ -z "${hit}" ]; then
echo "warning: ${soname} not found in standard lib paths" >&2
return 0
fi
# Follow the symlink to the real file, copy it, then recreate the symlink.
local real
real=$(readlink -f "${hit}")
cp -v "${real}" "${LIB_DIR}/"
local real_base
real_base=$(basename "${real}")
if [ "${real_base}" != "${soname}" ]; then
ln -sf "${real_base}" "${LIB_DIR}/${soname}"
fi
}
copy_with_symlinks libnuma.so.1
copy_with_symlinks libgomp.so.1
echo "vllm packaging completed successfully"
ls -liah "${LIB_DIR}/"